© 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. 8213
    Prev
    Next
    INDEX
    Explanations

    references to a specific location ("Aber") within the context of a news article

    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
    646
    +0.11
    0.5%
    578
    +0.11
    0.5%
    596
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.02
    326
    +0.11
    0.02
    284
    +0.10
    0.02
    Negative Logits
    atform
    -0.88
    iers
    -0.81
    TPS
    -0.79
    ipeg
    -0.79
    ership
    -0.77
    iets
    -0.77
    ingham
    -0.75
    ivity
    -0.73
    ergic
    -0.72
    iating
    -0.71
    POSITIVE LOGITS
    ration
    1.14
    rant
    1.00
    rations
    0.92
    deen
    0.86
    thur
    0.85
    ansas
    0.82
    rants
    0.78
    rious
    0.76
    rated
    0.73
    odied
    0.71
    Activations Density 0.046%

    No Known Activations