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. 21772
    Prev
    Next
    INDEX
    Explanations

    positive adjectives related to quality

    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
    373
    +0.10
    0.5%
    535
    +0.10
    0.5%
    146
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    406
    +0.10
    0.03
    284
    +0.10
    0.02
    Negative Logits
     Zamb
    -0.68
    ĸļ
    -0.64
     Adin
    -0.64
     duly
    -0.63
     Slater
    -0.60
     Sheriff
    -0.60
     Nieto
    -0.60
    cific
    -0.56
     complimentary
    -0.56
    hov
    -0.55
    POSITIVE LOGITS
    ainment
    1.04
    astic
    0.92
    ech
    0.91
    ournament
    0.89
    astical
    0.88
    itious
    0.85
    hent
    0.84
    hetical
    0.80
    ures
    0.79
    agraph
    0.76
    Activations Density 0.050%

    No Known Activations