© 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. 3790
    Prev
    Next
    INDEX
    Explanations

    distinct programming syntax and structure

    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
    497
    +0.17
    0.8%
    306
    +0.11
    0.5%
    194
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.17
    0.02
    487
    +0.11
    0.01
    331
    +0.10
    0.01
    Negative Logits
    ruary
    -0.83
    GBT
    -0.80
    nesday
    -0.79
    illon
    -0.76
    onica
    -0.76
    aiman
    -0.74
    auri
    -0.73
     Eliot
    -0.73
    orea
    -0.73
    ardi
    -0.72
    POSITIVE LOGITS
     Tit
    0.71
     converted
    0.68
     typed
    0.61
    cooked
    0.61
     istg
    0.60
     pestic
    0.60
     reinstated
    0.59
    ufficient
    0.58
     Entered
    0.58
     innocuous
    0.57
    Activations Density 0.042%

    No Known Activations