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 3072
    5. 8-RES_FS3072-JB
    6. 1435
    Prev
    Next
    INDEX
    Explanations

    comments or quotes related to a specific person mentioned in the text

    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
    6
    +0.14
    0.7%
    430
    +0.13
    0.6%
    255
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.11
    255
    +0.13
    0.08
    430
    +0.12
    0.08
    Negative Logits
     reven
    -0.75
     aven
    -0.68
     dracon
    -0.66
    untarily
    -0.66
    wcsstore
    -0.65
     expended
    -0.65
     tremend
    -0.65
    ¥ŀ
    -0.65
    isman
    -0.65
     ingestion
    -0.65
    POSITIVE LOGITS
    <|endoftext|>
    1.12
     Adds
    1.10
    ↵
    1.04
     [/
    1.01
    [/
    0.95
     Asked
    0.94
     Related
    0.94
    ↵↵
    0.94
     Refer
    0.90
     âĢķ
    0.90
    Activations Density 0.506%

    No Known Activations