© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    summaries and conclusions in the text

    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
    100
    +0.11
    0.5%
    173
    +0.11
    0.5%
    157
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.11
    0.03
    508
    +0.11
    0.03
    173
    +0.11
    0.03
    Negative Logits
    pires
    -0.96
    pora
    -0.73
    kered
    -0.72
     anymore
    -0.70
    tones
    -0.69
    erity
    -0.67
    pired
    -0.67
    emaker
    -0.67
    adata
    -0.67
     recre
    -0.66
    POSITIVE LOGITS
     conclud
    0.79
     abbrevi
    0.77
     checklist
    0.76
    Analysis
    0.72
     standings
    0.70
     synopsis
    0.69
     shenan
    0.68
     overview
    0.67
    Summary
    0.65
     minus
    0.65
    Activations Density 0.508%

    No Known Activations