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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20053
    Prev
    Next
    INDEX
    Explanations

    legal terms and procedural actions

    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
    746
    +0.12
    0.6%
    555
    +0.11
    0.5%
    229
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.12
    0.02
    746
    +0.11
    0.02
    176
    +0.10
    0.01
    Negative Logits
    ISM
    -0.70
     Abyssal
    -0.68
     Squid
    -0.68
     Danish
    -0.64
     Lions
    -0.64
     Italians
    -0.64
    OTS
    -0.63
     Chop
    -0.62
     dots
    -0.62
     Welsh
    -0.62
    POSITIVE LOGITS
    cription
    1.36
    chool
    1.34
    ervation
    1.32
    byter
    1.28
    umed
    1.25
    idents
    1.21
    idium
    1.19
    umably
    1.17
    idency
    1.16
    erving
    1.16
    Activations Density 0.024%

    No Known Activations