© 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 49152
    9. 8-RES_FS49152-JB
    11. 42925
    Prev
    Next
    INDEX
    Explanations

    references to distance or remoteness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    362
    +0.12
    0.5%
    288
    +0.11
    0.5%
    169
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.12
    0.01
    362
    +0.11
    0.01
    422
    +0.10
    0.01
    Negative Logits
    lain
    -0.97
    ingen
    -0.92
    udeb
    -0.88
    ickson
    -0.88
    umen
    -0.87
    leck
    -0.83
    ilts
    -0.81
    ounce
    -0.80
    inen
    -0.79
    Ĥİ
    -0.76
    POSITIVE LOGITS
     relatives
    1.06
     cousins
    1.00
     cousin
    1.00
     distant
    0.98
     neighbours
    0.91
     ancestors
    0.86
     neighbour
    0.84
     shores
    0.81
     kindred
    0.79
     ancestor
    0.79
    Activations Density 0.010%

    No Known Activations