© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    references to the BBC and its related programming or reports

    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
    631
    +0.11
    0.5%
    354
    +0.10
    0.5%
    424
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.11
    0.03
    519
    +0.10
    0.03
    386
    +0.10
    0.03
    Negative Logits
    eering
    -0.74
     coh
    -0.73
     Coch
    -0.68
    cal
    -0.67
     Costco
    -0.66
     recip
    -0.66
    zed
    -0.64
    chu
    -0.63
    cy
    -0.63
    incent
    -0.61
    POSITIVE LOGITS
     comedians
    0.80
    gypt
    0.75
     Nottingham
    0.74
     apologise
    0.73
     Wales
    0.70
    atform
    0.70
     analysed
    0.69
     cartoons
    0.69
     ][
    0.67
     presenter
    0.67
    Activations Density 0.453%

    No Known Activations