© 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. 3834
    Prev
    Next
    INDEX
    Explanations

    expressions related to tracking and monitoring activities or entities

    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
    218
    +0.14
    0.7%
    342
    +0.13
    0.6%
    580
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    342
    +0.14
    0.02
    581
    +0.13
    0.02
    580
    +0.13
    0.02
    Negative Logits
     disapp
    -0.72
    awaru
    -0.72
    ////
    -0.71
    icter
    -0.69
    inction
    -0.69
    odon
    -0.68
    icum
    -0.67
    pret
    -0.66
    BUG
    -0.66
    operator
    -0.66
    POSITIVE LOGITS
     folders
    0.86
     Activities
    0.74
     Cullen
    0.71
     activities
    0.70
     transmissions
    0.70
     metabolites
    0.68
     directories
    0.68
     Activity
    0.68
     activity
    0.67
     nearest
    0.66
    Activations Density 0.234%

    No Known Activations