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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 153
    Prev
    Next
    INDEX
    Explanations

    information related to financial terms and transactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    508
    +0.12
    0.5%
    195
    +0.10
    0.5%
    651
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.03
    725
    +0.10
    0.03
    79
    +0.10
    0.03
    Negative Logits
    wright
    -0.91
    lda
    -0.90
    achev
    -0.85
    artisan
    -0.84
    liga
    -0.82
    enes
    -0.81
    dinand
    -0.79
    holes
    -0.79
    phal
    -0.79
    uve
    -0.78
    POSITIVE LOGITS
     installments
    1.11
     occurrence
    0.99
     subscription
    0.93
     specials
    0.91
     intervals
    0.91
     servings
    0.88
     basis
    0.87
    ized
    0.87
     fluctuations
    0.87
     dose
    0.86
    Activations Density 0.076%

    No Known Activations