© 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. 3569
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names related to individuals or characters

    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
    210
    +0.12
    0.5%
    465
    +0.10
    0.5%
    767
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.02
    492
    +0.10
    0.01
    210
    +0.10
    0.01
    Negative Logits
    ateurs
    -0.72
    iably
    -0.62
    cause
    -0.62
    amn
    -0.60
    uous
    -0.59
    uously
    -0.59
     shame
    -0.59
    picking
    -0.57
    WER
    -0.57
    ¬¼
    -0.56
    POSITIVE LOGITS
     Centauri
    0.74
    angan
    0.70
    iron
    0.68
    uin
    0.66
    ä½ľ
    0.63
    Wan
    0.63
    ģ«
    0.62
    opal
    0.62
    nan
    0.61
    ilib
    0.61
    Activations Density 0.044%

    No Known Activations