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 24576
    5. 8-RES_FS24576-JB
    6. 11655
    Prev
    Next
    INDEX
    Explanations

    words related to clothing items

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.12
    0.6%
    332
    +0.11
    0.5%
    536
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.01
    326
    +0.11
    0.01
    114
    +0.10
    0.01
    Negative Logits
    Raw
    -0.77
    Demand
    -0.66
    REDACTED
    -0.64
    Reply
    -0.63
    Planet
    -0.62
    rawdownloadcloneembedreportprint
    -0.61
    paces
    -0.60
    éĹĺ
    -0.60
    Launch
    -0.59
    SpaceEngineers
    -0.59
    POSITIVE LOGITS
    ige
    1.15
    ments
    1.14
    igious
    1.12
    igation
    1.03
    igators
    0.99
     vest
    0.95
    ig
    0.93
    ees
    0.92
    ment
    0.87
    igator
    0.87
    Activations Density 0.025%

    No Known Activations