© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22405
    Prev
    Next
    INDEX
    Explanations

    instances of public scrutiny or criticism directed at individuals, particularly in the context of personal struggles and societal perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.21
    1.0%
    373
    +0.19
    0.9%
    160
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.10
    160
    +0.19
    0.10
    442
    +0.13
    0.09
    Negative Logits
     payroll
    -0.94
    ĪĴ
    -0.92
     consolid
    -0.81
     civilian
    -0.80
     consolidate
    -0.79
     uranium
    -0.78
     favoring
    -0.78
     antitrust
    -0.77
     favorably
    -0.76
     stabilize
    -0.75
    POSITIVE LOGITS
    Scroll
    1.63
    Speaking
    1.23
    Writing
    1.20
    However
    1.20
    VIDEO
    1.18
    His
    1.17
    Advertisement
    1.16
    Pict
    1.16
    Parents
    1.15
    Actor
    1.15
    Activations Density 0.283%

    No Known Activations