© 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. 31305
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or delimiters in the text

    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
    55
    +0.10
    0.5%
    261
    +0.10
    0.5%
    102
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    297
    +0.10
    0.06
    546
    +0.10
    0.05
    43
    +0.10
    0.04
    Negative Logits
    aceae
    -0.80
     Theft
    -0.77
    ibrary
    -0.76
    =>
    -0.73
    imation
    -0.70
    ancial
    -0.69
    =-=-=-=-
    -0.69
    ahime
    -0.67
    士
    -0.66
    utations
    -0.66
    POSITIVE LOGITS
     noticing
    1.48
     realizing
    1.43
     fearing
    1.35
     sensing
    1.31
     disgusted
    1.28
     horrified
    1.24
     encountering
    1.23
     frustrated
    1.22
     baffled
    1.22
     unable
    1.22
    Activations Density 0.379%

    No Known Activations