© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4074
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting variations within the text

    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
    71
    +0.13
    0.6%
    709
    +0.11
    0.5%
    603
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.13
    0.05
    101
    +0.11
    -0.01
    709
    +0.10
    0.05
    Negative Logits
    washer
    -0.76
    naire
    -0.72
    eat
    -0.69
    tc
    -0.68
    cern
    -0.67
    76561
    -0.67
    soever
    -0.66
    itaire
    -0.65
     worries
    -0.64
    nir
    -0.64
    POSITIVE LOGITS
    Stat
    0.74
     compositions
    0.72
     unpublished
    0.66
    )[
    0.64
    hemy
    0.64
     Annex
    0.64
     authenticated
    0.64
     Yankee
    0.61
     handwritten
    0.61
    Field
    0.60
    Activations Density 1.425%

    No Known Activations