© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5233
    Prev
    Next
    INDEX
    Explanations

    words related to the concepts of "red" and "rod."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.14
    0.7%
    326
    +0.10
    0.5%
    652
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.14
    0.02
    316
    +0.10
    0.02
    701
    +0.10
    0.02
    Negative Logits
    apo
    -0.74
     citiz
    -0.71
    imates
    -0.69
    ahi
    -0.63
    ubis
    -0.63
    chens
    -0.60
    bern
    -0.60
    emis
    -0.58
    que
    -0.58
     favors
    -0.57
    POSITIVE LOGITS
    ynam
    1.02
    ynamic
    0.99
    ollar
    0.78
    inson
    0.77
    ership
    0.75
    iol
    0.75
    igate
    0.71
    hair
    0.69
    hands
    0.66
    orf
    0.65
    Activations Density 0.144%

    No Known Activations