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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5548
    Prev
    Next
    INDEX
    Explanations

    references to government laws and regulations or political figures

    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
    288
    +0.13
    0.6%
    752
    +0.10
    0.5%
    357
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.13
    0.05
    409
    +0.10
    0.04
    508
    +0.10
    0.04
    Negative Logits
    enger
    -0.80
    Dog
    -0.76
    enes
    -0.75
    pered
    -0.75
    lihood
    -0.71
    bane
    -0.71
     Tycoon
    -0.70
    Maker
    -0.70
    bringer
    -0.69
    hots
    -0.68
    POSITIVE LOGITS
     government
    0.95
     appellate
    0.95
     judiciary
    0.92
     agencies
    0.92
     agency
    0.87
    ism
    0.83
     Reserve
    0.82
    ized
    0.82
     courthouse
    0.81
    ists
    0.80
    Activations Density 0.134%

    No Known Activations