© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5247
    Prev
    Next
    INDEX
    Explanations

    references to the word "Mil" or its variants, indicating a focus on a specific term or name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    16
    +0.13
    0.6%
    21
    +0.13
    0.6%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.13
    0.01
    288
    +0.13
    0.01
    21
    +0.13
    0.01
    Negative Logits
    LY
    -0.70
     depreciation
    -0.65
     Artemis
    -0.65
     compr
    -0.63
    IELD
    -0.63
    eers
    -0.61
     stern
    -0.60
    BOOK
    -0.60
     cider
    -0.60
    Ħ¢
    -0.59
    POSITIVE LOGITS
    waukee
    1.31
    estones
    1.23
    estone
    1.15
    ksh
    1.04
    ieu
    0.99
    isec
    0.97
    gram
    0.95
    pas
    0.83
    itary
    0.82
    aceutical
    0.82
    Activations Density 0.056%

    No Known Activations