© 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. 3721
    Prev
    Next
    INDEX
    Explanations

    the presence of individuals in a narrative context, particularly their roles and actions

    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
    605
    +0.13
    0.6%
    410
    +0.10
    0.5%
    696
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.13
    0.08
    545
    +0.10
    0.08
    169
    +0.10
    0.07
    Negative Logits
    utenberg
    -0.65
     Cthulhu
    -0.63
     Goodman
    -0.57
    owsky
    -0.54
    thus
    -0.53
     Savings
    -0.53
    ettle
    -0.53
     karma
    -0.53
     Weaver
    -0.53
     Hastings
    -0.52
    POSITIVE LOGITS
    actionDate
    0.69
    )].
    0.68
    icipated
    0.67
    soever
    0.64
    assi
    0.62
    pired
    0.60
    tailed
    0.60
    :'
    0.60
     Mehran
    0.59
    qt
    0.59
    Activations Density 2.008%

    No Known Activations