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. 11486
    Prev
    Next
    INDEX
    Explanations

    places and political entities in a document

    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
    481
    +0.19
    0.9%
    33
    +0.12
    0.6%
    718
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.19
    0.05
    288
    +0.12
    0.06
    401
    +0.11
    0.05
    Negative Logits
     Dover
    -0.74
    eatures
    -0.70
     Stain
    -0.70
    gradient
    -0.70
    olid
    -0.59
    ãĥĥãĥĪ
    -0.59
     Simpl
    -0.59
    Tags
    -0.58
    uesday
    -0.57
    inse
    -0.56
    POSITIVE LOGITS
     who
    0.97
    who
    0.95
     whom
    0.93
     swear
    0.77
    whose
    0.75
     willing
    0.73
     eaves
    0.72
     interested
    0.71
    hari
    0.69
    untled
    0.69
    Activations Density 0.330%

    No Known Activations