© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1838
    Prev
    Next
    INDEX
    Explanations

    times and timings

    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
    238
    +0.10
    0.4%
    93
    +0.09
    0.4%
    251
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.10
    0.03
    132
    +0.09
    0.03
    468
    +0.09
    0.03
    Negative Logits
    Reviewer
    -0.68
    esome
    -0.61
    anty
    -0.59
    aple
    -0.55
    ittal
    -0.55
    )/
    -0.55
    phasis
    -0.54
    asis
    -0.54
    ortion
    -0.53
    acco
    -0.53
    POSITIVE LOGITS
    etheless
    1.13
     afternoon
    1.11
     morning
    1.10
    morning
    1.10
     mornings
    1.00
     evening
    0.98
    aneously
    0.97
    night
    0.94
     Thursday
    0.92
     Wednesday
    0.88
    Activations Density 0.070%

    No Known Activations