© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4535
    Prev
    Next
    INDEX
    Explanations

    concepts related to research and clinical applications in scientific fields

    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
    214
    +0.11
    0.5%
    91
    +0.10
    0.4%
    251
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.11
    0.14
    338
    +0.10
    0.16
    214
    +0.10
    0.09
    Negative Logits
    ?).
    -0.91
    ?)
    -0.82
    !).
    -0.77
    .)
    -0.77
    ipedia
    -0.76
    ...)
    -0.76
    ).
    -0.74
    Laughs
    -0.74
    })
    -0.74
    -)
    -0.73
    POSITIVE LOGITS
     Plaintiff
    0.87
     Defendant
    0.80
     presiding
    0.77
     {*
    0.76
     proposition
    0.75
     consent
    0.74
     Address
    0.73
     affirmative
    0.73
     appellant
    0.72
     Seller
    0.71
    Activations Density 29.398%

    No Known Activations