© 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 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. 12415
    Prev
    Next
    INDEX
    Explanations

    streets, locations, and political figures

    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
    71
    +0.12
    0.6%
    462
    +0.10
    0.5%
    616
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.12
    0.02
    344
    +0.10
    0.02
    71
    +0.10
    0.02
    Negative Logits
    achu
    -0.75
    LAN
    -0.73
    Hub
    -0.72
    hub
    -0.72
    helps
    -0.70
    izont
    -0.70
    Activity
    -0.69
    Helper
    -0.69
    aucus
    -0.69
    Broad
    -0.69
    POSITIVE LOGITS
     thousand
    1.20
     percent
    1.07
    teen
    1.02
     hundred
    1.00
     cents
    0.98
    een
    0.97
    eenth
    0.92
     million
    0.89
     pounds
    0.84
     hours
    0.83
    Activations Density 0.029%

    No Known Activations