© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    phrases that signify purpose or justification

    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
    50
    +0.10
    0.5%
    29
    +0.09
    0.4%
    352
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.10
    0.04
    50
    +0.09
    0.04
    353
    +0.09
    0.04
    Negative Logits
    ipher
    -0.83
    united
    -0.75
    Haunted
    -0.74
    occupied
    -0.72
    cephal
    -0.70
    encrypted
    -0.70
    yss
    -0.70
    cit
    -0.69
    HF
    -0.68
    ypes
    -0.68
    POSITIVE LOGITS
     divergence
    0.77
     continu
    0.75
     discrepancy
    0.74
     variance
    0.71
    ã
    0.66
     discrepancies
    0.64
    gat
    0.63
     evolution
    0.63
     deviation
    0.63
     variation
    0.62
    Activations Density 0.077%

    No Known Activations