© 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. 3853
    Prev
    Next
    INDEX
    Explanations

    references to places, dates, and significant events or achievements

    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
    481
    +0.26
    1.3%
    459
    +0.12
    0.5%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.26
    0.27
    264
    +0.12
    0.08
    232
    +0.09
    0.13
    Negative Logits
     brakes
    -0.67
    RESULTS
    -0.65
     uphill
    -0.65
     inhib
    -0.63
     intimidation
    -0.60
     behold
    -0.60
     superiors
    -0.60
    Fed
    -0.58
    theless
    -0.57
    uly
    -0.56
    POSITIVE LOGITS
    querque
    0.77
    enegger
    0.76
    arbon
    0.67
    orest
    0.66
    )",
    0.66
    atform
    0.65
    itia
    0.65
    ipel
    0.63
    axies
    0.61
    £ı
    0.61
    Activations Density 10.592%

    No Known Activations