© 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. 27229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "im."

    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
    667
    +0.11
    0.5%
    247
    +0.11
    0.5%
    631
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    713
    +0.11
    0.01
    314
    +0.11
    0.00
    667
    +0.10
    0.01
    Negative Logits
     Cth
    -0.71
     Nazis
    -0.69
     Twelve
    -0.65
     weights
    -0.64
     shell
    -0.64
     Titanic
    -0.63
    eers
    -0.62
     choice
    -0.62
    iesel
    -0.62
     puzzles
    -0.60
    POSITIVE LOGITS
    posing
    1.39
    mediate
    1.35
    mediately
    1.34
    agin
    1.33
    plementation
    1.33
    perial
    1.32
    plement
    1.29
    minent
    1.28
    manuel
    1.24
    ported
    1.22
    Activations Density 0.179%

    No Known Activations