© 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. 4755
    Prev
    Next
    INDEX
    Explanations

    words related to news events and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    480
    +0.33
    1.7%
    481
    +0.29
    1.4%
    447
    +0.26
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.33
    0.12
    481
    +0.29
    0.09
    480
    +0.26
    0.01
    Negative Logits
     srf
    -0.67
    ecause
    -0.60
    [_
    -0.57
     alike
    -0.56
    Ĭ±
    -0.55
     *.
    -0.55
    aturdays
    -0.53
     |--
    -0.53
     macro
    -0.52
    incinn
    -0.51
    POSITIVE LOGITS
    ieth
    0.67
    CVE
    0.61
     itself
    0.59
    's
    0.59
    liest
    0.59
    iest
    0.59
    atories
    0.58
    seys
    0.58
    forts
    0.57
    orative
    0.55
    Activations Density 0.818%

    No Known Activations