Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41440
    Prev
    Next
    INDEX
    Explanations

    words that signify talent or skill

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    339
    +0.12
    0.6%
    111
    +0.12
    0.5%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    499
    +0.12
    0.01
    339
    +0.11
    0.01
    Negative Logits
    ptions
    -0.80
    patch
    -0.75
    ĸļ
    -0.74
    FACE
    -0.73
    phrine
    -0.72
    thur
    -0.68
    ocene
    -0.65
     coli
    -0.65
    ©¶æ
    -0.63
    vention
    -0.63
    POSITIVE LOGITS
    ness
    0.99
     talents
    0.94
     minds
    0.92
    nesses
    0.87
     young
    0.87
     talent
    0.85
     musicians
    0.83
     individuals
    0.81
     youngsters
    0.81
    glers
    0.78
    Activations Density 0.013%

    No Known Activations