© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    instances of the word "toss" and its variations, indicating actions of throwing or discarding

    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
    681
    +0.10
    0.5%
    368
    +0.10
    0.5%
    585
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.10
    0.02
    180
    +0.10
    0.03
    351
    +0.09
    0.02
    Negative Logits
     Uri
    -0.70
    ãĥķãĤ©
    -0.69
     Barrier
    -0.68
    Streamer
    -0.67
     Stru
    -0.67
    STER
    -0.66
    ORT
    -0.65
     Sloan
    -0.65
     Tens
    -0.64
    ECA
    -0.64
    POSITIVE LOGITS
    yip
    0.84
     gigg
    0.83
    jri
    0.78
    cloth
    0.75
    pload
    0.73
    pole
    0.72
     toes
    0.71
    fing
    0.70
    nown
    0.70
    ciating
    0.70
    Activations Density 0.239%

    No Known Activations