© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    platforms for social interaction and communication

    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
    373
    +0.11
    0.5%
    548
    +0.10
    0.4%
    25
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.11
    0.02
    573
    +0.10
    0.02
    25
    +0.09
    0.02
    Negative Logits
    tein
    -0.79
    inas
    -0.75
    ilic
    -0.67
    cill
    -0.64
    endiary
    -0.64
    ennes
    -0.64
    ilts
    -0.63
     enthusi
    -0.63
    restrial
    -0.63
    Catal
    -0.62
    POSITIVE LOGITS
    lihood
    2.13
    liest
    1.05
    minded
    1.00
    liness
    1.00
    lier
    0.95
    ability
    0.94
     minded
    0.91
    joy
    0.85
    able
    0.81
    ably
    0.76
    Activations Density 0.039%

    No Known Activations