© 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. 3243
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or relationships in context

    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
    +0.12
    0.5%
    21
    +0.12
    0.5%
    40
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.12
    0.03
    417
    +0.12
    0.04
    418
    +0.12
    0.03
    Negative Logits
    Finish
    -0.72
    meet
    -0.67
    ileged
    -0.66
    ses
    -0.65
    meric
    -0.64
    oran
    -0.63
    Chip
    -0.63
    IDE
    -0.62
    OH
    -0.59
     Champion
    -0.59
    POSITIVE LOGITS
    pmwiki
    0.96
     pse
    0.86
     ILCS
    0.76
     precaution
    0.67
     prohibitions
    0.66
     perspect
    0.66
     opio
    0.64
     horm
    0.63
     laun
    0.63
    =#
    0.63
    Activations Density 0.321%

    No Known Activations