Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 4540
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal restrictions and prohibitions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    403
    +0.12
    0.5%
    447
    +0.11
    0.5%
    529
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.12
    0.06
    507
    +0.11
    0.07
    608
    +0.10
    0.08
    Negative Logits
     partName
    -0.78
    Revolution
    -0.70
    swick
    -0.68
    Cmd
    -0.66
    POSE
    -0.64
    Plot
    -0.63
    hematic
    -0.63
    plan
    -0.61
    JC
    -0.61
     Finder
    -0.59
    POSITIVE LOGITS
     allowable
    0.94
     exceptions
    0.83
     issuance
    0.83
     employers
    0.83
     minors
    0.82
     nonprofits
    0.81
     municipalities
    0.81
     discretionary
    0.81
     applicants
    0.80
     permissible
    0.80
    Activations Density 0.878%

    No Known Activations