© 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. 3756
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specifications related to computer hardware and performance

    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
    373
    +0.13
    0.6%
    238
    +0.12
    0.6%
    391
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.13
    0.03
    29
    +0.12
    0.03
    640
    +0.10
    0.04
    Negative Logits
    acc
    -0.80
    voc
    -0.73
    kins
    -0.73
    sn
    -0.72
    sur
    -0.72
    Reply
    -0.72
    rising
    -0.72
    mist
    -0.71
    rob
    -0.71
    gnu
    -0.70
    POSITIVE LOGITS
     NETWORK
    0.72
     Monument
    0.69
    0000000
    0.69
     GAM
    0.68
     Showdown
    0.67
     Mub
    0.66
     Ashes
    0.66
    ITIES
    0.65
     Basketball
    0.65
     Transmission
    0.64
    Activations Density 0.337%

    No Known Activations