© 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. 26865
    Prev
    Next
    INDEX
    Explanations

    references to navigation elements and actions in a digital or website context

    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
    6
    +0.11
    0.5%
    463
    +0.10
    0.5%
    407
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.11
    0.06
    209
    +0.10
    0.05
    556
    +0.10
    0.04
    Negative Logits
     coh
    -0.83
     endors
    -0.72
     princ
    -0.71
     advoc
    -0.71
     spice
    -0.70
    ciating
    -0.69
    wana
    -0.67
     accomp
    -0.66
     whis
    -0.66
     livest
    -0.65
    POSITIVE LOGITS
    ","
    1.31
    "],"
    1.14
    ̶
    1.09
    ._
    1.00
    |
    0.99
    \.
    0.96
    Âł
    0.92
    "],
    0.91
    .","
    0.90
    ["
    0.90
    Activations Density 0.626%

    No Known Activations