© 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 EvalsExportsAPI 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. 30499
    Prev
    Next
    INDEX
    Explanations

    quotation marks and spoken dialogue in text

    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
    160
    +0.19
    0.9%
    314
    +0.16
    0.7%
    107
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.19
    0.06
    102
    +0.16
    0.05
    107
    +0.14
    0.04
    Negative Logits
     gram
    -0.74
     choir
    -0.74
     hurricane
    -0.74
     shock
    -0.74
     thorn
    -0.73
     tanker
    -0.73
     dred
    -0.73
     spitting
    -0.73
     bitters
    -0.72
     irony
    -0.72
    POSITIVE LOGITS
    Apply
    1.52
    Allow
    1.45
    Enable
    1.37
    Recommended
    1.34
    Create
    1.33
    Find
    1.32
    Edit
    1.32
    Add
    1.32
    Use
    1.31
    >"
    1.30
    Activations Density 0.130%

    No Known Activations