© 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. 26896
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to statistics and scores

    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
    505
    +0.11
    0.5%
    442
    +0.11
    0.5%
    242
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.03
    387
    +0.11
    0.02
    584
    +0.11
    0.02
    Negative Logits
     technically
    -0.73
    ciating
    -0.71
     shutter
    -0.67
     established
    -0.67
     unnecessary
    -0.66
     margins
    -0.66
     Tanz
    -0.66
     centimeters
    -0.66
     crammed
    -0.63
     converted
    -0.63
    POSITIVE LOGITS
    bard
    1.18
    14
    1.14
    11
    1.11
    13
    1.07
    15
    1.07
    12
    1.05
    20
    1.04
    21
    1.04
    17
    1.03
    27
    1.02
    Activations Density 0.110%

    No Known Activations