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

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4482
    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
    758
    +0.10
    0.4%
    380
    +0.10
    0.4%
    526
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.10
    393
    +0.10
    0.08
    608
    +0.09
    0.09
    Negative Logits
     Jiu
    -0.65
    cession
    -0.60
    ffic
    -0.60
     Negro
    -0.59
     Whit
    -0.59
     Hipp
    -0.58
     Tir
    -0.58
     Mess
    -0.57
    gregation
    -0.56
     Ranch
    -0.54
    POSITIVE LOGITS
     like
    1.10
    like
    0.93
     LIKE
    0.85
     alike
    0.85
     occasional
    0.85
    such
    0.77
    maybe
    0.76
    mes
    0.76
    Īè
    0.75
    sort
    0.74
    Activations Density 0.675%

    No Known Activations