© 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. 11878
    Prev
    Next
    INDEX
    Explanations

    historical names and terms

    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
    404
    +0.12
    0.6%
    182
    +0.11
    0.5%
    711
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.12
    0.03
    373
    +0.11
    -0.01
    711
    +0.10
    0.01
    Negative Logits
    ndra
    -0.69
    owe
    -0.69
    abwe
    -0.67
    steen
    -0.66
    oso
    -0.63
    akeru
    -0.62
    nyder
    -0.62
    ghai
    -0.60
    ippi
    -0.59
     Kaf
    -0.59
    POSITIVE LOGITS
    ulhu
    0.90
    INAL
    0.86
    ishops
    0.72
    ©¶æ
    0.71
    agos
    0.66
    eal
    0.65
    ®
    0.64
    Truth
    0.64
    final
    0.64
    ROM
    0.63
    Activations Density 0.059%

    No Known Activations