© 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. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3788
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    359
    +0.10
    0.5%
    491
    +0.10
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.10
    0.18
    575
    +0.10
    0.11
    65
    +0.10
    0.10
    Negative Logits
    cius
    -0.88
    nce
    -0.86
    ned
    -0.79
     âĸ
    -0.78
    nie
    -0.74
    ny
    -0.74
    hern
    -0.71
    ********
    -0.71
     Kand
    -0.68
    ne
    -0.67
    POSITIVE LOGITS
    folio
    0.74
     Citiz
    0.72
    ©¶æ¥µ
    0.71
     registrations
    0.69
     Registration
    0.65
     pestic
    0.65
     Frie
    0.65
    CLASSIFIED
    0.64
     ende
    0.64
     indexed
    0.63
    Activations Density 4.186%

    No Known Activations