© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    references to rankings or numerical placements in competitive contexts

    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
    78
    +0.11
    0.5%
    388
    +0.11
    0.5%
    704
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.11
    0.13
    153
    +0.11
    0.17
    417
    +0.11
    0.13
    Negative Logits
     IMAGES
    -0.90
    etimes
    -0.82
    ebin
    -0.77
     ³³
    -0.76
     Replay
    -0.74
     EVENTS
    -0.72
     confirm
    -0.72
     NET
    -0.71
     [];
    -0.71
     WARN
    -0.71
    POSITIVE LOGITS
    pires
    0.82
    adra
    0.82
    pired
    0.75
    omorphic
    0.74
     ornament
    0.74
    agall
    0.72
    ocrat
    0.71
    gemony
    0.70
    olitan
    0.68
     decor
    0.68
    Activations Density 25.625%

    No Known Activations