© 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. 16228
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and historical facts

    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
    191
    +0.11
    0.5%
    756
    +0.10
    0.5%
    546
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.09
    43
    +0.10
    0.08
    765
    +0.09
    0.08
    Negative Logits
    ahu
    -0.80
    »Ĵ
    -0.76
    eem
    -0.73
    kees
    -0.73
    oward
    -0.71
    onym
    -0.70
    ire
    -0.68
    姫
    -0.67
    inately
    -0.66
    Alias
    -0.65
    POSITIVE LOGITS
     whereas
    1.07
     namely
    1.06
     culminating
    1.04
     resulting
    1.01
     although
    0.98
     which
    0.95
     prompting
    0.94
     whereby
    0.94
     hence
    0.89
     exacerbated
    0.88
    Activations Density 0.372%

    No Known Activations