© 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 24576
    9. 8-RES_FS24576-JB
    11. 22066
    Prev
    Next
    INDEX
    Explanations

    references to the immune system and its components

    oai_token-act-pair · gpt-4o-miniTriggered 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
    496
    +0.12
    0.5%
    83
    +0.11
    0.5%
    422
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.12
    0.02
    516
    +0.11
    0.02
    83
    +0.11
    0.01
    Negative Logits
    \\\\\\\\
    -0.84
    ivia
    -0.75
    AU
    -0.74
    76561
    -0.73
    */(
    -0.73
    hare
    -0.71
    ilts
    -0.69
    google
    -0.68
     Mond
    -0.68
     Afric
    -0.67
    POSITIVE LOGITS
     glob
    0.85
     deficiency
    0.84
    mediated
    0.83
     immune
    0.82
    ogl
    0.79
     infiltrate
    0.79
    obl
    0.78
     defences
    0.77
     checkpoint
    0.77
     defenses
    0.76
    Activations Density 0.015%

    No Known Activations