© 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. 27634
    Prev
    Next
    INDEX
    Explanations

    technical specifications and configuration details related to Java

    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
    373
    +0.17
    0.8%
    326
    +0.11
    0.5%
    396
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.04
    579
    +0.11
    0.04
    524
    +0.10
    0.03
    Negative Logits
     charism
    -0.77
     metic
    -0.74
     appell
    -0.69
    icans
    -0.68
     chants
    -0.65
    isphere
    -0.63
     intimidation
    -0.63
    SPONSORED
    -0.62
     rhetorical
    -0.61
    aukee
    -0.59
    POSITIVE LOGITS
    ubuntu
    1.21
    beta
    1.10
    stable
    0.92
    EngineDebug
    0.89
    201
    0.88
    Beta
    0.88
    VERSION
    0.88
    alpha
    0.86
     beta
    0.85
    Release
    0.83
    Activations Density 0.162%

    No Known Activations