© 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. 41614
    Prev
    Next
    INDEX
    Explanations

    references to news outlets and media sources

    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
    378
    +0.11
    0.5%
    291
    +0.10
    0.4%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    547
    +0.11
    0.04
    317
    +0.10
    0.04
    115
    +0.10
    0.04
    Negative Logits
     veter
    -0.67
    animate
    -0.64
     diaper
    -0.59
     harms
    -0.56
     causal
    -0.55
    atible
    -0.54
     surgical
    -0.54
     parity
    -0.54
    pires
    -0.54
     doesnt
    -0.52
    POSITIVE LOGITS
    .
    0.84
     quoted
    0.77
    .</
    0.76
     rhet
    0.74
     quoting
    0.73
    .]
    0.70
    .).
    0.69
     sarcast
    0.69
    ."
    0.67
    lied
    0.67
    Activations Density 0.145%

    No Known Activations