© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations and locations

    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
    648
    +0.11
    0.5%
    71
    +0.10
    0.4%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.08
    480
    +0.10
    0.08
    664
    +0.09
    0.06
    Negative Logits
     experien
    -0.95
     elig
    -0.81
     enthusi
    -0.79
     compan
    -0.78
    anwhile
    -0.75
    âĹ¼
    -0.74
     apex
    -0.74
     nostalg
    -0.73
     citiz
    -0.73
     occas
    -0.72
    POSITIVE LOGITS
     Dear
    0.68
    usha
    0.67
     Barbie
    0.67
     Aden
    0.66
    Dad
    0.66
    Daddy
    0.65
    Girls
    0.65
     (%
    0.64
     Islam
    0.64
     Laden
    0.64
    Activations Density 3.525%

    No Known Activations