© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    variations of the word "up."

    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
    +0.20
    0.9%
    99
    +0.11
    0.5%
    156
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.02
    114
    +0.11
    0.03
    298
    +0.10
    0.03
    Negative Logits
    imi
    -0.85
    orius
    -0.73
    ativity
    -0.73
    adr
    -0.71
    Condition
    -0.70
    ĸļ
    -0.70
    gement
    -0.69
    Released
    -0.69
    ative
    -0.69
    cca
    -0.68
    POSITIVE LOGITS
    phrine
    0.80
    ModLoader
    0.79
     Carbuncle
    0.77
     Pelicans
    0.75
     eleph
    0.74
     Byr
    0.73
     GOODMAN
    0.71
     looph
    0.69
     Elk
    0.69
     comr
    0.69
    Activations Density 2.321%

    No Known Activations