© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to assessments or measurements

    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
    735
    +0.13
    0.6%
    391
    +0.11
    0.5%
    583
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.13
    0.02
    415
    +0.11
    0.03
    583
    +0.10
    0.03
    Negative Logits
     skim
    -0.77
    SHARE
    -0.72
    elight
    -0.71
     burner
    -0.69
     discs
    -0.69
    -$
    -0.67
    Quantity
    -0.67
     fares
    -0.67
    Buzz
    -0.66
     tabl
    -0.63
    POSITIVE LOGITS
    ivot
    0.94
    agi
    0.90
    oland
    0.89
    ija
    0.83
    OPE
    0.82
    uez
    0.81
    oso
    0.79
    oman
    0.78
    bably
    0.78
    onomous
    0.77
    Activations Density 0.205%

    No Known Activations