© 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. 19725
    Prev
    Next
    INDEX
    Explanations

    references to personal stories and reflections on identity and acceptance

    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
    178
    +0.10
    0.5%
    425
    +0.09
    0.4%
    517
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.10
    0.04
    178
    +0.09
    0.04
    517
    +0.09
    0.04
    Negative Logits
    GF
    -0.70
    aut
    -0.69
    bishop
    -0.66
    pac
    -0.64
    zar
    -0.63
    ACH
    -0.63
    BD
    -0.60
    Ķ
    -0.60
    Detailed
    -0.60
    afer
    -0.59
    POSITIVE LOGITS
     it
    0.74
     he
    0.69
     they
    0.69
     pandemonium
    0.66
     however
    0.65
     she
    0.65
    untled
    0.64
     chances
    0.64
     citing
    0.62
    enment
    0.62
    Activations Density 0.165%

    No Known Activations