© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    elements related to service efficacy and critique

    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
    281
    +0.12
    0.6%
    239
    +0.09
    0.4%
    364
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.12
    0.18
    554
    +0.09
    0.29
    426
    +0.09
    0.16
    Negative Logits
    azon
    -0.69
    jri
    -0.60
    Iv
    -0.59
     Bast
    -0.58
    LV
    -0.57
    ¥µ
    -0.57
     adj
    -0.56
    veyard
    -0.55
    hammad
    -0.55
     Zika
    -0.54
    POSITIVE LOGITS
    theless
    0.72
    DragonMagazine
    0.64
     experien
    0.63
    enum
    0.63
    dimension
    0.63
     derog
    0.63
    uddenly
    0.63
    asio
    0.62
    amorph
    0.62
     unavoid
    0.60
    Activations Density 29.586%

    No Known Activations