© 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. 8-RES_POST_32K-OAI
    11. 8698
    Prev
    Next
    INDEX
    Explanations

    numerals and hyphens used in statistics or data representation

    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
    508
    +0.11
    0.5%
    717
    +0.11
    0.5%
    715
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.02
    497
    +0.11
    0.03
    359
    +0.10
    0.03
    Negative Logits
    ĸļ
    -0.79
    sbm
    -0.65
     extrad
    -0.59
     directions
    -0.59
     veins
    -0.58
     reborn
    -0.57
    ãĥīãĥ©
    -0.57
     abdom
    -0.57
    chains
    -0.56
     Nept
    -0.56
    POSITIVE LOGITS
    cially
    0.95
    ulating
    0.75
    reau
    0.74
    ulative
    0.72
    leneck
    0.72
    oland
    0.72
    ayson
    0.71
    ulates
    0.70
    iful
    0.69
    icipated
    0.68
    Activations Density 0.339%

    No Known Activations