© 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. 27536
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "take" and its variations, indicating a focus on actions or considerations

    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
    736
    +0.12
    0.6%
    677
    +0.11
    0.5%
    277
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.12
    0.07
    402
    +0.11
    0.06
    240
    +0.11
    0.05
    Negative Logits
    cia
    -0.75
    ":"","
    -0.71
    rek
    -0.69
    rake
    -0.61
    ãĤ¦
    -0.60
    ãĥ¢
    -0.59
    uster
    -0.59
     Tuc
    -0.58
    ||||
    -0.58
    kt
    -0.58
    POSITIVE LOGITS
     into
    1.16
    into
    0.98
     account
    0.91
     Into
    0.91
     INTO
    0.88
     considerations
    0.73
     consideration
    0.71
     Account
    0.70
    aways
    0.68
     accounts
    0.67
    Activations Density 0.295%

    No Known Activations