© 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. 30288
    Prev
    Next
    INDEX
    Explanations

    verbs in various forms and tenses

    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
    264
    +0.10
    0.5%
    156
    +0.10
    0.4%
    251
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.10
    0.03
    762
    +0.10
    0.04
    351
    +0.10
    0.03
    Negative Logits
    usterity
    -0.83
     horm
    -0.63
     pse
    -0.63
    amas
    -0.58
    ipel
    -0.57
    iken
    -0.55
    iband
    -0.55
    ?????-
    -0.54
     dou
    -0.54
     shenan
    -0.54
    POSITIVE LOGITS
     whenever
    0.85
     when
    0.83
     elsewhere
    0.83
     throughout
    0.81
     today
    0.78
     here
    0.77
     during
    0.75
     everywhere
    0.71
     tonight
    0.70
     before
    0.69
    Activations Density 0.389%

    No Known Activations