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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 355
    Prev
    Next
    INDEX
    Explanations

    questions related to self-reflection and self-doubt

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    412
    +0.12
    0.5%
    331
    +0.11
    0.5%
    615
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.12
    0.09
    638
    +0.11
    0.08
    374
    +0.10
    0.04
    Negative Logits
    inery
    -0.78
    iHUD
    -0.76
    ©¶æ¥µ
    -0.74
    abba
    -0.69
    alde
    -0.67
     pione
    -0.67
    20439
    -0.67
    abor
    -0.66
    tails
    -0.65
    jong
    -0.64
    POSITIVE LOGITS
    ?
    1.98
    ?:
    1.86
    ?"
    1.82
    ?'
    1.82
    ?)
    1.76
    ?),
    1.72
    ?",
    1.72
    ?).
    1.70
    ?!
    1.70
    ...?
    1.69
    Activations Density 2.787%

    No Known Activations