© 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. 8834
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or titles, particularly related to individuals or organizations

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    218
    +0.10
    0.5%
    214
    +0.10
    0.4%
    368
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    503
    +0.10
    0.02
    588
    +0.10
    0.02
    Negative Logits
    isted
    -0.73
    isting
    -0.68
    ements
    -0.67
    ModLoader
    -0.67
    ishly
    -0.67
    ocked
    -0.66
    ised
    -0.65
    istry
    -0.64
    EMENT
    -0.62
    iful
    -0.62
    POSITIVE LOGITS
    leans
    0.82
    rolet
    0.81
    rane
    0.79
    poon
    0.78
    bles
    0.77
    ben
    0.77
    bie
    0.77
    riel
    0.76
    ran
    0.75
    riad
    0.75
    Activations Density 0.071%

    No Known Activations