© 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. 3581
    Prev
    Next
    INDEX
    Explanations

    references to mockups and mock drafts, particularly in relation to design and proposals

    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
    608
    +0.11
    0.5%
    532
    +0.10
    0.4%
    445
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    532
    +0.11
    0.02
    301
    +0.10
    0.02
    201
    +0.10
    0.02
    Negative Logits
     actionGroup
    -0.93
     GOODMAN
    -0.79
    aez
    -0.77
    ondo
    -0.69
    enough
    -0.69
     JA
    -0.67
    rance
    -0.67
    OA
    -0.67
    ributes
    -0.65
     trave
    -0.64
    POSITIVE LOGITS
     caric
    0.85
     caricature
    0.79
     mock
    0.78
     satir
    0.75
     stereotype
    0.73
    aughs
    0.72
     tropes
    0.69
     masc
    0.69
     humor
    0.69
     vampires
    0.68
    Activations Density 0.372%

    No Known Activations