© 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 3072
    9. 8-RES_FS3072-JB
    11. 792
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or sending messages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    59
    +0.14
    0.7%
    322
    +0.10
    0.5%
    437
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.06
    439
    +0.10
    0.05
    654
    +0.10
    0.04
    Negative Logits
    theless
    -0.74
    heid
    -0.73
    walker
    -0.63
    urity
    -0.63
    phe
    -0.62
    profit
    -0.61
    haven
    -0.59
    tera
    -0.58
    sit
    -0.58
     pores
    -0.57
    POSITIVE LOGITS
    inel
    1.08
    keys
    0.92
    enced
    0.91
    entious
    0.89
     condolences
    0.89
    ãĥĥãĥī
    0.88
    imental
    0.83
     forth
    0.78
     invitations
    0.78
    mail
    0.75
    Activations Density 0.501%

    No Known Activations