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 3072
    5. 8-RES_FS3072-JB
    6. 1009
    Prev
    Next
    INDEX
    Explanations

    commands or instructions in multiple languages involving installation and computer file handling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    104
    +0.12
    0.5%
    230
    +0.11
    0.5%
    367
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.12
    0.06
    659
    +0.11
    0.07
    232
    +0.10
    0.07
    Negative Logits
    793
    -0.71
     XCOM
    -0.68
    Zone
    -0.67
    883
    -0.66
     Encounter
    -0.66
    owicz
    -0.66
     TNT
    -0.65
     UPDATE
    -0.65
     Terminator
    -0.64
     Turner
    -0.63
    POSITIVE LOGITS
    grad
    0.88
    fg
    0.87
    GY
    0.81
    gee
    0.79
     Lilly
    0.75
    roleum
    0.73
    bie
    0.73
    IOR
    0.72
    ebted
    0.72
    ãĥ©
    0.71
    Activations Density 1.142%

    No Known Activations