© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    statements related to thoughts and beliefs

    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
    524
    +0.14
    0.7%
    314
    +0.14
    0.6%
    13
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.14
    0.05
    698
    +0.14
    0.05
    271
    +0.12
    0.04
    Negative Logits
     Scores
    -0.63
     Virtue
    -0.58
     contrace
    -0.57
     Divinity
    -0.56
     pse
    -0.55
    Soc
    -0.55
     melanch
    -0.54
    itaire
    -0.53
    ais
    -0.53
     Answers
    -0.53
    POSITIVE LOGITS
     twice
    1.06
     Twice
    0.94
     possible
    0.90
    ever
    0.83
    ivable
    0.77
    ceivable
    0.76
     anything
    0.76
     slightest
    0.73
    osal
    0.73
     anymore
    0.72
    Activations Density 0.713%

    No Known Activations