© 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 EvalsExportsinterp-engineNEWAPI 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. 7393
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    726
    +0.15
    0.7%
    430
    +0.11
    0.5%
    100
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.04
    373
    +0.11
    -0.02
    701
    +0.08
    0.03
    Negative Logits
     maximal
    -0.71
     telev
    -0.67
     discrep
    -0.65
     decimal
    -0.62
     cryptoc
    -0.62
     Helic
    -0.61
     unanim
    -0.61
     stalled
    -0.60
     dawn
    -0.60
     conver
    -0.60
    POSITIVE LOGITS
    rex
    1.05
    llo
    0.95
    rina
    0.93
    ouse
    0.90
    ancy
    0.90
    amus
    0.87
    brook
    0.87
    hof
    0.86
    neum
    0.85
    igans
    0.84
    Activations Density 0.255%

    No Known Activations