© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    references to problematic situations or conditions

    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
    422
    +0.11
    0.5%
    59
    +0.10
    0.5%
    741
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.11
    0.03
    699
    +0.10
    0.03
    740
    +0.10
    0.02
    Negative Logits
    ¨
    -0.82
     ped
    -0.72
     surpr
    -0.68
     chops
    -0.67
    âĢ¢
    -0.66
    ãĤ¦ãĤ¹
    -0.65
     whiff
    -0.64
    enhagen
    -0.63
     comed
    -0.63
    izont
    -0.62
    POSITIVE LOGITS
     Minecraft
    0.68
    mods
    0.67
    reci
    0.66
     Seraph
    0.65
     Order
    0.65
    quartered
    0.64
    ourcing
    0.64
     Ord
    0.63
    voy
    0.63
    gal
    0.62
    Activations Density 0.278%

    No Known Activations