© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    314
    +0.13
    0.6%
    71
    +0.12
    0.6%
    260
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.09
    223
    +0.12
    0.07
    693
    +0.11
    0.07
    Negative Logits
    ettings
    -0.76
    medi
    -0.66
    venge
    -0.64
    tern
    -0.63
    plement
    -0.61
    vati
    -0.60
    hers
    -0.60
    plan
    -0.59
    bear
    -0.59
    que
    -0.58
    POSITIVE LOGITS
    %
    1.34
    %"
    1.28
    %-
    1.28
     percent
    1.21
     Minutes
    1.16
    %.
    1.11
     minutes
    1.09
    mins
    1.07
    Hz
    1.06
    %:
    1.06
    Activations Density 0.176%

    No Known Activations