© 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 1536
    9. 8-RES_FS1536-JB
    11. 1535
    Prev
    Next
    INDEX
    Explanations

    addresses or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    176
    +0.15
    0.7%
    479
    +0.13
    0.6%
    588
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.15
    0.10
    479
    +0.13
    0.08
    530
    +0.10
    0.08
    Negative Logits
    noticed
    -0.84
    advertisement
    -0.77
    entimes
    -0.76
    months
    -0.75
    istically
    -0.74
    cffffcc
    -0.73
    deal
    -0.73
    pleasant
    -0.70
    informed
    -0.70
    attribute
    -0.70
    POSITIVE LOGITS
     Ibid
    1.07
     Mal
    1.02
     Lad
    1.01
     Cyr
    1.01
     Kenn
    1.00
     Kat
    1.00
     Nat
    0.99
     Pent
    0.99
     Lav
    0.98
     Tar
    0.98
    Activations Density 2.589%

    No Known Activations