© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    quotations that signify notable descriptions or characterizations

    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
    +0.14
    0.7%
    741
    +0.10
    0.5%
    122
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.14
    0.05
    418
    +0.10
    0.05
    581
    +0.10
    0.04
    Negative Logits
     Yog
    -0.67
    mare
    -0.67
     alternating
    -0.64
     Hos
    -0.62
     scrimmage
    -0.61
     gmaxwell
    -0.60
    âĸĦ
    -0.60
     tale
    -0.59
     Beth
    -0.59
     Yoshi
    -0.58
    POSITIVE LOGITS
    untled
    0.97
    cit
    0.92
    cci
    0.80
     Furious
    0.80
    cffff
    0.79
    soDeliveryDate
    0.79
    20439
    0.78
    osponsors
    0.76
    ira
    0.75
    ikuman
    0.74
    Activations Density 0.975%

    No Known Activations