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. 5389
    Prev
    Next
    INDEX
    Explanations

    things related to legal proceedings, government activities, and formalities

    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
    762
    +0.11
    0.5%
    197
    +0.11
    0.5%
    398
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.10
    348
    +0.11
    0.09
    246
    +0.09
    0.08
    Negative Logits
    "!
    -0.89
    !",
    -0.69
     Droid
    -0.63
    !".
    -0.62
    ãĤ¹ãĥĪ
    -0.60
    ulent
    -0.60
    '),
    -0.60
    "),
    -0.59
     Redmond
    -0.58
     %%
    -0.57
    POSITIVE LOGITS
    entimes
    1.05
     yeah
    1.04
    laughs
    0.96
     secondly
    0.95
     uh
    0.94
     everybody
    0.86
     frankly
    0.84
    Basically
    0.84
    ertodd
    0.83
     basically
    0.83
    Activations Density 1.588%

    No Known Activations