© 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. 4489
    Prev
    Next
    INDEX
    Explanations

    phrases concerning existence, particularly in relation to different identities or concepts

    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
    263
    +0.12
    0.5%
    69
    +0.10
    0.4%
    760
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.12
    0.02
    177
    +0.10
    0.02
    622
    +0.10
    0.01
    Negative Logits
    washing
    -0.77
    ician
    -0.76
    vous
    -0.76
    arching
    -0.76
    izon
    -0.75
    ussen
    -0.73
    umatic
    -0.72
     Mehran
    -0.71
    oult
    -0.70
    ousy
    -0.69
    POSITIVE LOGITS
     psi
    0.71
     subter
    0.70
     fossils
    0.68
     Fein
    0.68
     existence
    0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.66
     viable
    0.65
     individuality
    0.64
     uniqueness
    0.64
     biochemical
    0.64
    Activations Density 0.053%

    No Known Activations