© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4029
    Prev
    Next
    INDEX
    Explanations

    numeric data and references to events or conferences

    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
    145
    +0.13
    0.6%
    3
    +0.11
    0.5%
    506
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.13
    0.04
    33
    +0.11
    0.04
    257
    +0.10
    0.04
    Negative Logits
     hinge
    -0.69
     favor
    -0.64
    sheets
    -0.63
     apiece
    -0.63
    rift
    -0.63
     gestation
    -0.62
    )</
    -0.62
    gotten
    -0.61
    .}
    -0.61
     reven
    -0.60
    POSITIVE LOGITS
     Amateur
    0.80
    ateur
    0.69
    essim
    0.69
     Guys
    0.69
    ombo
    0.68
     Dating
    0.67
    oso
    0.66
    UST
    0.65
     Residents
    0.65
     Reporting
    0.65
    Activations Density 0.244%

    No Known Activations