© 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. 27046
    Prev
    Next
    INDEX
    Explanations

    documents or references that involve formal communication or reports

    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
    386
    +0.11
    0.5%
    547
    +0.10
    0.5%
    5
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.11
    0.08
    547
    +0.10
    0.06
    679
    +0.10
    0.09
    Negative Logits
    iencies
    -0.71
    vantage
    -0.69
    cause
    -0.68
    ymes
    -0.68
     breeds
    -0.66
    !/
    -0.66
    planet
    -0.64
    mins
    -0.63
    atically
    -0.62
    ynchron
    -0.62
    POSITIVE LOGITS
     published
    1.15
     accompanying
    1.13
     released
    1.08
     dated
    1.03
     obtained
    0.96
     quoted
    0.96
     cited
    0.95
     titled
    0.93
     posted
    0.91
     entitled
    0.91
    Activations Density 1.193%

    No Known Activations