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 49152
    5. 8-RES_FS49152-JB
    6. 43154
    Prev
    Next
    INDEX
    Explanations

    verbs related to influence and impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    685
    +0.11
    0.5%
    679
    +0.11
    0.5%
    252
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.11
    0.03
    206
    +0.11
    0.02
    431
    +0.10
    0.02
    Negative Logits
     Fever
    -0.58
     Wag
    -0.56
     Pesh
    -0.56
     plur
    -0.54
     owl
    -0.54
     Votes
    -0.54
     sweats
    -0.54
     phased
    -0.54
    é¾įå
    -0.53
    onet
    -0.53
    POSITIVE LOGITS
    .</
    0.81
    .?
    0.72
    .<
    0.70
    .[
    0.69
     us
    0.69
    .
    0.69
     entail
    0.67
    .;
    0.66
    ?,
    0.65
    .):
    0.64
    Activations Density 0.066%

    No Known Activations