© 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. 28259
    Prev
    Next
    INDEX
    Explanations

    references to the need for further research and development

    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
    +0.13
    0.6%
    355
    +0.12
    0.6%
    604
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.13
    0.06
    459
    +0.12
    0.04
    540
    +0.10
    0.07
    Negative Logits
     Disapp
    -0.72
    die
    -0.72
     veto
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    ãĥĥãĥī
    -0.64
     constitu
    -0.63
    cius
    -0.63
     disappeared
    -0.63
     ninety
    -0.63
    orno
    -0.63
    POSITIVE LOGITS
     warranted
    0.95
     eluc
    0.87
    urther
    0.84
     examining
    0.76
     longitudinal
    0.75
     urgently
    0.75
     exploring
    0.75
     clarification
    0.74
     refine
    0.73
     clarify
    0.71
    Activations Density 0.956%

    No Known Activations