© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    specific dates and references to actions or events related to the month of May

    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
    732
    +0.11
    0.5%
    219
    +0.10
    0.5%
    609
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.11
    0.03
    29
    +0.10
    0.04
    277
    +0.10
    0.02
    Negative Logits
     Predator
    -0.68
    vantage
    -0.67
    Champ
    -0.65
    ensible
    -0.64
     Limbaugh
    -0.63
    ¯
    -0.62
    apist
    -0.62
    roup
    -0.62
    orest
    -0.61
    ournal
    -0.60
    POSITIVE LOGITS
     herself
    0.80
     ILCS
    0.70
    sted
    0.62
     cosmetics
    0.61
     Gardens
    0.61
     bos
    0.60
     favourite
    0.59
     WTO
    0.59
    CTV
    0.59
    airy
    0.58
    Activations Density 1.154%

    No Known Activations