© 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. 8109
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, or plots in a document

    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
    373
    +0.15
    0.7%
    314
    +0.12
    0.6%
    36
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.05
    107
    +0.12
    0.05
    317
    +0.12
    0.04
    Negative Logits
     Reborn
    -0.79
     Runes
    -0.68
     Bans
    -0.67
     Reincarn
    -0.65
     cloaked
    -0.65
     Tribunal
    -0.65
     Vampire
    -0.62
     Dominican
    -0.61
     Oprah
    -0.61
     Ragnarok
    -0.61
    POSITIVE LOGITS
    ĩ
    0.99
    ures
    0.98
    erences
    0.92
    isodes
    0.89
    endix
    0.87
    Ī
    0.87
    URE
    0.85
    Figure
    0.84
    ITION
    0.83
    cially
    0.83
    Activations Density 0.218%

    No Known Activations