© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "at" in various contexts

    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
    373
    +0.17
    0.8%
    258
    +0.09
    0.4%
    547
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.04
    514
    +0.09
    0.03
    352
    +0.09
    0.04
    Negative Logits
    omething
    -0.79
    inary
    -0.75
    erto
    -0.61
    weather
    -0.57
    elsius
    -0.57
     Celest
    -0.56
    ulic
    -0.56
    tle
    -0.56
    ndra
    -0.56
    Tube
    -0.55
    POSITIVE LOGITS
     pp
    1.04
     seq
    0.96
    ¶
    0.78
     ___
    0.76
     ¶
    0.75
     cx
    0.75
     chapters
    0.72
     ãĤ
    0.71
     pages
    0.71
    Chapter
    0.69
    Activations Density 0.123%

    No Known Activations