© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4286
    Prev
    Next
    INDEX
    Explanations

    mentions of events or gatherings related to attendance

    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
    497
    +0.11
    0.5%
    347
    +0.11
    0.5%
    171
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.11
    0.03
    270
    +0.11
    0.02
    505
    +0.11
    0.02
    Negative Logits
     ===
    -0.65
     ðŁij
    -0.64
     GDDR
    -0.64
     Swed
    -0.63
    pecting
    -0.62
    enance
    -0.62
    soType
    -0.61
    _-
    -0.61
     Zeal
    -0.60
     ¯
    -0.60
    POSITIVE LOGITS
    iann
    0.81
    ettlement
    0.80
    arter
    0.78
    gewater
    0.73
     graduation
    0.73
    ilater
    0.70
    idency
    0.70
    orgetown
    0.70
    psey
    0.69
    alia
    0.69
    Activations Density 0.231%

    No Known Activations