© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7738
    Prev
    Next
    INDEX
    Explanations

    references to specific alpha autoantibodies and their relevance in psychiatric conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    549
    +0.12
    0.5%
    725
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.12
    0.01
    116
    +0.11
    0.01
    317
    +0.09
    0.01
    Negative Logits
    dayName
    -0.77
    ickr
    -0.76
     externalToEVAOnly
    -0.75
     ILCS
    -0.74
    cit
    -0.73
    iage
    -0.72
     Dres
    -0.66
    ipop
    -0.66
    ourse
    -0.65
    assium
    -0.65
    POSITIVE LOGITS
    ĭ
    0.94
    į
    0.80
    resses
    0.80
    uran
    0.77
    liest
    0.75
    wart
    0.74
    ement
    0.74
    ¶æ
    0.73
    irst
    0.73
    omatic
    0.73
    Activations Density 0.050%

    No Known Activations