© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4605
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and email subscriptions

    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
    521
    +0.10
    0.5%
    167
    +0.10
    0.4%
    125
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.10
    0.02
    194
    +0.10
    0.02
    399
    +0.09
    0.02
    Negative Logits
    nesota
    -0.68
    stood
    -0.66
    bender
    -0.65
    conom
    -0.64
    edi
    -0.62
    uthor
    -0.62
    76561
    -0.62
    inois
    -0.60
     transpired
    -0.58
    Footnote
    -0.58
    POSITIVE LOGITS
    selves
    0.96
     own
    0.76
    Interstitial
    0.72
     ourselves
    0.70
     newest
    0.69
     selves
    0.68
     latest
    0.67
     motto
    0.66
     respective
    0.66
     homepage
    0.65
    Activations Density 0.020%

    No Known Activations