© 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. 26785
    Prev
    Next
    INDEX
    Explanations

    symbols and words related to digital or programming contexts, particularly those indicating actions or status

    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
    565
    +0.12
    0.5%
    373
    +0.11
    0.5%
    663
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.12
    0.01
    643
    +0.11
    0.00
    77
    +0.10
    0.00
    Negative Logits
    stery
    -0.83
    urger
    -0.74
    çIJ
    -0.69
     burg
    -0.69
    ĨĴ
    -0.67
     unspecified
    -0.67
    ç·
    -0.67
    urg
    -0.67
    orian
    -0.66
    gey
    -0.66
    POSITIVE LOGITS
     Became
    0.79
     Array
    0.79
     Introduced
    0.68
     Actions
    0.64
     Passed
    0.63
     EVENTS
    0.60
    tnc
    0.59
    wcsstore
    0.57
     lets
    0.57
     Towards
    0.56
    Activations Density 0.013%

    No Known Activations