© 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. 22386
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to negative impacts and consequences

    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
    481
    +0.20
    0.9%
    218
    +0.12
    0.5%
    745
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.05
    703
    +0.12
    0.04
    218
    +0.10
    0.04
    Negative Logits
    istry
    -0.78
    ãĤ±
    -0.73
    ODY
    -0.72
    OLOG
    -0.72
    Aim
    -0.71
    Laughs
    -0.71
    Pic
    -0.70
    enth
    -0.69
    NES
    -0.69
    eye
    -0.69
    POSITIVE LOGITS
     disasters
    1.00
     Hurricane
    0.99
     accidents
    0.94
     untreated
    0.93
     negligence
    0.89
     illness
    0.88
     crashes
    0.88
     collapsing
    0.88
     erosion
    0.86
     pollution
    0.86
    Activations Density 0.243%

    No Known Activations