© 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. 3909
    Prev
    Next
    INDEX
    Explanations

    references to Major League Baseball (MLB) divisions and teams

    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
    314
    +0.14
    0.7%
    702
    +0.12
    0.6%
    672
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.14
    0.08
    314
    +0.12
    0.07
    490
    +0.11
    0.07
    Negative Logits
    sels
    -0.67
     Nau
    -0.66
     RL
    -0.64
    Military
    -0.63
     vulner
    -0.63
     arrang
    -0.61
     Latter
    -0.61
     nevertheless
    -0.61
     marines
    -0.61
    lift
    -0.60
    POSITIVE LOGITS
    ĸļ
    1.00
    ãĥĥãĥī
    0.86
    ¬¼
    0.80
    ibrary
    0.78
    ozo
    0.77
    azeera
    0.75
    querque
    0.74
    mia
    0.74
    à¼
    0.73
    idia
    0.73
    Activations Density 0.454%

    No Known Activations