© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1999
    Prev
    Next
    INDEX
    Explanations

    technical factors or considerations

    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
    195
    +0.14
    0.6%
    459
    +0.11
    0.5%
    623
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.14
    0.02
    540
    +0.11
    0.02
    623
    +0.10
    0.02
    Negative Logits
    alach
    -0.84
    ©¶æ
    -0.82
    oÄŁ
    -0.79
    dos
    -0.76
    gem
    -0.75
    phis
    -0.75
     Seym
    -0.72
    arus
    -0.71
    guyen
    -0.71
    velt
    -0.71
    POSITIVE LOGITS
     contributing
    0.90
     factors
    0.89
     affecting
    0.89
     influencing
    0.89
     factor
    0.88
    factor
    0.84
     determining
    0.79
     Factors
    0.77
     equation
    0.77
     impacting
    0.76
    Activations Density 0.027%

    No Known Activations