© 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. 5463
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical symbols and notations

    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
    578
    +0.14
    0.6%
    102
    +0.11
    0.5%
    308
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    719
    +0.14
    0.09
    489
    +0.11
    0.08
    127
    +0.10
    0.07
    Negative Logits
    liness
    -0.79
     succession
    -0.69
    orative
    -0.68
    ITNESS
    -0.68
    liest
    -0.67
     manag
    -0.65
     Shroud
    -0.62
    ality
    -0.62
    itaire
    -0.61
    ruciating
    -0.61
    POSITIVE LOGITS
    α
    1.23
    ε
    1.17
    ο
    1.08
    ι
    1.08
    Ï
    0.94
    Î
    0.93
    ¸
    0.92
    ķ
    0.88
    ãĥĥãĥī
    0.88
    ³
    0.86
    Activations Density 0.308%

    No Known Activations