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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 43469
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and feelings conveyed through metaphoric language

    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
    314
    +0.13
    0.6%
    372
    +0.12
    0.5%
    675
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.13
    0.12
    372
    +0.12
    0.10
    720
    +0.10
    0.10
    Negative Logits
     Tanz
    -0.72
     Seym
    -0.68
     Container
    -0.67
     Commons
    -0.67
     Opportun
    -0.66
     Folk
    -0.64
     Monroe
    -0.64
     Lancaster
    -0.64
     RAF
    -0.62
     Samar
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.24
    udes
    0.95
    agree
    0.93
    tal
    0.92
    ude
    0.88
    âĤ¬
    0.84
    ti
    0.83
    exist
    0.82
    tu
    0.82
    dro
    0.82
    Activations Density 0.328%

    No Known Activations