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 3072
    5. 8-RES_FS3072-JB
    6. 1817
    Prev
    Next
    INDEX
    Explanations

    mentions of special or extraordinary events or circumstances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    710
    +0.10
    0.5%
    729
    +0.10
    0.4%
    590
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    590
    +0.10
    0.04
    345
    +0.10
    0.05
    251
    +0.10
    0.04
    Negative Logits
    amus
    -0.64
    ·
    -0.62
    kj
    -0.62
     Twain
    -0.60
    nington
    -0.60
     Couch
    -0.59
    absolute
    -0.59
    ylon
    -0.57
     Webster
    -0.57
    shown
    -0.56
    POSITIVE LOGITS
    ties
    1.23
    ised
    1.23
    izations
    1.07
    isations
    1.06
    ities
    0.93
    ized
    0.92
    ty
    0.91
    ises
    0.89
    isable
    0.89
     relativity
    0.85
    Activations Density 0.592%

    No Known Activations