© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and scoring systems

    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
    84
    +0.11
    0.5%
    71
    +0.11
    0.5%
    497
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.11
    0.01
    657
    +0.11
    0.01
    445
    +0.11
    0.01
    Negative Logits
    DEN
    -0.70
     urgently
    -0.70
    OPLE
    -0.69
     FACE
    -0.66
    FTWARE
    -0.65
    âĹ¼
    -0.64
    £ı
    -0.64
     ['
    -0.63
    Accessory
    -0.63
     âĢ¦"
    -0.63
    POSITIVE LOGITS
    姫
    0.64
     mesmer
    0.60
     Glac
    0.60
    bf
    0.59
     rav
    0.59
     Difficulty
    0.59
     Enemies
    0.58
     perv
    0.57
    great
    0.56
    1945
    0.55
    Activations Density 0.032%

    No Known Activations