© 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. 30441
    Prev
    Next
    INDEX
    Explanations

    words or prefixes indicating a sense of separation or division

    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
    640
    +0.09
    0.4%
    389
    +0.09
    0.4%
    533
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.09
    0.02
    167
    +0.09
    0.01
    238
    +0.09
    0.02
    Negative Logits
     Generation
    -0.70
     Sisters
    -0.63
     breeze
    -0.60
     Rubin
    -0.58
     Gork
    -0.57
     Prompt
    -0.56
     Keane
    -0.56
     Isabel
    -0.56
     Ples
    -0.56
    UTH
    -0.55
    POSITIVE LOGITS
    concert
    1.11
    heart
    1.07
    orient
    0.99
    ench
    0.99
    respected
    0.97
    loc
    0.96
    interested
    0.96
    semb
    0.96
    array
    0.96
    affected
    0.96
    Activations Density 0.074%

    No Known Activations