© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26587
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of user requirements and actions in instructional or technical contexts

    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
    30
    +0.10
    0.5%
    321
    +0.09
    0.4%
    171
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.10
    0.09
    49
    +0.09
    0.09
    326
    +0.09
    0.06
    Negative Logits
    "}],"
    -0.69
     )]
    -0.69
    avement
    -0.64
    Bul
    -0.63
    apor
    -0.61
     Syndrome
    -0.61
     whistlebl
    -0.59
    imize
    -0.58
    iferation
    -0.58
    harm
    -0.58
    POSITIVE LOGITS
     manually
    0.93
    know
    0.77
    ername
    0.72
     permission
    0.69
     individually
    0.65
     knowledge
    0.64
     purchased
    0.63
    76561
    0.62
    marked
    0.62
     approval
    0.60
    Activations Density 0.284%

    No Known Activations