© 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. 27315
    Prev
    Next
    INDEX
    Explanations

    references to visual perspectives and scenic views

    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
    564
    +0.11
    0.5%
    113
    +0.11
    0.5%
    702
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.11
    0.07
    113
    +0.11
    0.04
    377
    +0.10
    0.07
    Negative Logits
    die
    -0.75
     plur
    -0.74
    ycle
    -0.68
    aml
    -0.65
     Rebell
    -0.65
     Lifetime
    -0.63
    ickers
    -0.62
     recy
    -0.62
    riter
    -0.61
     habitual
    -0.61
    POSITIVE LOGITS
     overhead
    1.05
     downstairs
    1.03
     upstairs
    1.03
     overlooking
    1.01
     through
    0.97
     inland
    0.95
     inside
    0.92
     balcon
    0.92
     northeast
    0.91
     east
    0.90
    Activations Density 0.915%

    No Known Activations