© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics, particularly time stamps and percentages

    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
    218
    +0.19
    0.9%
    745
    +0.18
    0.9%
    420
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.19
    0.06
    745
    +0.18
    0.08
    373
    +0.16
    0.01
    Negative Logits
    chuk
    -0.68
    [/
    -0.63
     seamlessly
    -0.58
     combines
    -0.57
     lasted
    -0.57
     airflow
    -0.57
     surfaced
    -0.56
     Clarks
    -0.56
     [âĢ¦]
    -0.56
     existed
    -0.56
    POSITIVE LOGITS
    CLASSIFIED
    1.00
    emi
    0.81
    chance
    0.73
    chu
    0.73
    intend
    0.71
    uma
    0.71
    numbered
    0.70
    call
    0.70
    nil
    0.68
    soType
    0.67
    Activations Density 1.389%

    No Known Activations