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. 23154
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "Col" which may refer to "College" or "Colonel."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    314
    +0.11
    0.5%
    109
    +0.11
    0.5%
    192
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.11
    0.02
    192
    +0.11
    0.01
    85
    +0.10
    0.01
    Negative Logits
     Werewolf
    -0.74
    natureconservancy
    -0.65
    ARP
    -0.64
    cffffcc
    -0.63
    visor
    -0.63
     forth
    -0.62
    CHAT
    -0.61
    ARK
    -0.60
    IELD
    -0.58
    PROV
    -0.58
    POSITIVE LOGITS
    ossal
    1.30
    onel
    1.21
    ombo
    1.12
    umbo
    1.11
    onial
    1.11
    ossus
    1.07
    leen
    1.06
    ophon
    1.03
    oured
    1.02
    ored
    0.99
    Activations Density 0.017%

    No Known Activations