© 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. 31821
    Prev
    Next
    INDEX
    Explanations

    patterns related to names or titles

    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
    561
    +0.11
    0.5%
    699
    +0.10
    0.4%
    392
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.12
    314
    +0.10
    -0.02
    232
    +0.09
    0.09
    Negative Logits
    entin
    -0.85
    Downloadha
    -0.81
    accompan
    -0.74
    pring
    -0.73
    NRS
    -0.68
    etter
    -0.67
    xus
    -0.67
    ãģ®éŃĶ
    -0.65
    omial
    -0.64
    imens
    -0.64
    POSITIVE LOGITS
    abeth
    0.80
     Ae
    0.73
    bia
    0.73
    ipation
    0.72
    rated
    0.66
     coli
    0.66
     Pradesh
    0.64
    icism
    0.64
    ergy
    0.62
    rate
    0.61
    Activations Density 1.755%

    No Known Activations