© 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. 10-RES_POST_32K-OAI
    11. 32321
    Prev
    Next
    INDEX
    Explanations

    technical terms and numeric identifiers in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    307
    +0.11
    0.5%
    143
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.11
    0.04
    23
    +0.10
    0.03
    232
    +0.10
    0.04
    Negative Logits
     Percy
    -0.76
     Coil
    -0.72
    WOOD
    -0.71
    ascus
    -0.70
     Hopkins
    -0.68
     Spartan
    -0.67
     CO
    -0.67
     Bolt
    -0.66
     Spac
    -0.66
     carb
    -0.65
    POSITIVE LOGITS
    u
    1.80
    yu
    1.14
    eu
    1.10
    ucc
    1.07
    vu
    1.06
    uj
    1.05
    uin
    1.03
    uv
    1.03
    zu
    0.99
    uff
    0.97
    Activations Density 0.494%

    No Known Activations