© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4014
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific titles or categories related to events 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
    497
    +0.11
    0.5%
    505
    +0.11
    0.5%
    140
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.11
    0.01
    140
    +0.11
    0.01
    597
    +0.10
    0.01
    Negative Logits
    DAY
    -0.70
    Zip
    -0.68
    -)
    -0.66
     Jonah
    -0.64
     Prohibition
    -0.63
    Unknown
    -0.62
     *)
    -0.61
     steroids
    -0.61
     Newman
    -0.60
     Stern
    -0.60
    POSITIVE LOGITS
    phia
    0.90
     PsyNet
    0.79
    owship
    0.78
    kus
    0.76
    inki
    0.75
    ̶
    0.74
    idated
    0.74
    pees
    0.72
    hya
    0.72
    emale
    0.71
    Activations Density 0.055%

    No Known Activations