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. 11664
    Prev
    Next
    INDEX
    Explanations

    references to team members or individuals within a group

    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
    679
    +0.17
    0.8%
    497
    +0.15
    0.7%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.17
    0.03
    146
    +0.15
    0.02
    224
    +0.12
    0.02
    Negative Logits
    PDATE
    -0.75
    Scope
    -0.71
    trop
    -0.71
    MER
    -0.70
    BAT
    -0.68
    anche
    -0.65
     msec
    -0.65
    okin
    -0.63
    rawdownloadcloneembedreportprint
    -0.63
    STAR
    -0.63
    POSITIVE LOGITS
    hips
    1.70
    hip
    1.03
    ials
    0.89
    doms
    0.88
     who
    0.78
    hea
    0.77
    iosis
    0.77
     stationed
    0.76
    holders
    0.76
    ially
    0.76
    Activations Density 0.036%

    No Known Activations