© 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. 28439
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating correlation or association in research findings

    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
    455
    +0.13
    0.6%
    338
    +0.09
    0.4%
    716
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.07
    455
    +0.09
    0.07
    393
    +0.09
    0.07
    Negative Logits
    advertising
    -0.89
    whatever
    -0.79
    laughs
    -0.78
    pees
    -0.77
    nell
    -0.74
    daq
    -0.74
    ocrat
    -0.73
     Scare
    -0.73
    pee
    -0.73
    oho
    -0.73
    POSITIVE LOGITS
     consequently
    1.00
     hence
    0.97
    rost
    0.94
    rogen
    0.93
     decreased
    0.90
    rogens
    0.90
     therefore
    0.88
     subsequently
    0.87
     specificity
    0.87
     β
    0.85
    Activations Density 0.516%

    No Known Activations