© 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. 3846
    Prev
    Next
    INDEX
    Explanations

    time-related information or dates

    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
    459
    +0.15
    0.7%
    600
    +0.10
    0.5%
    417
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.15
    0.05
    197
    +0.10
    0.04
    685
    +0.09
    0.05
    Negative Logits
    /-
    -0.69
    tests
    -0.68
    opter
    -0.66
    uckles
    -0.64
    arus
    -0.64
    checks
    -0.63
    rams
    -0.63
    leys
    -0.58
     tests
    -0.58
    changes
    -0.58
    POSITIVE LOGITS
    imum
    0.70
    INTON
    0.69
     ransom
    0.68
     CITY
    0.67
     Leth
    0.67
    VILLE
    0.64
     Attention
    0.64
    hov
    0.63
    ELY
    0.62
    eele
    0.62
    Activations Density 0.180%

    No Known Activations