© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    periods and other punctuation marks that signal sentence endings

    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
    420
    +0.17
    0.8%
    745
    +0.13
    0.6%
    459
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.17
    0.04
    420
    +0.13
    0.01
    143
    +0.12
    0.03
    Negative Logits
     Dusk
    -0.72
    atre
    -0.68
    wed
    -0.64
    ë
    -0.63
    AMA
    -0.63
    ©¶æ
    -0.61
     trolls
    -0.61
     Terran
    -0.61
     Trees
    -0.60
    naissance
    -0.59
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.80
    itionally
    0.78
    olulu
    0.76
    ancial
    0.70
    quished
    0.68
    Reviewer
    0.67
    ificantly
    0.65
     Advertisement
    0.64
     Prix
    0.64
    hesion
    0.63
    Activations Density 0.507%

    No Known Activations