© 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. 27549
    Prev
    Next
    INDEX
    Explanations

    variables representing frequency-related data

    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
    314
    +0.15
    0.7%
    725
    +0.10
    0.5%
    27
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.15
    0.03
    678
    +0.10
    0.03
    158
    +0.10
    0.03
    Negative Logits
     Hep
    -0.71
     Wonderland
    -0.71
     reper
    -0.67
     solicitation
    -0.64
     rumor
    -0.64
     invitations
    -0.64
     Mayhem
    -0.63
     Feinstein
    -0.60
     Roundup
    -0.60
     TOUR
    -0.60
    POSITIVE LOGITS
    coord
    1.07
    Ax
    1.01
     coordinates
    1.00
    vel
    0.99
    axis
    0.98
     coordinate
    0.93
    aml
    0.88
    awn
    0.85
    ielding
    0.82
     coord
    0.82
    Activations Density 0.218%

    No Known Activations