© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    references to legal or financial liabilities and related conditions

    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
    660
    +0.12
    0.5%
    496
    +0.11
    0.5%
    412
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.02
    96
    +0.11
    0.02
    580
    +0.10
    0.02
    Negative Logits
    Wheel
    -0.77
    rencies
    -0.76
    Roaming
    -0.73
    Mas
    -0.72
    IJ
    -0.71
    BIP
    -0.70
    Iterator
    -0.69
    Wallet
    -0.69
    Wr
    -0.68
    Maps
    -0.67
    POSITIVE LOGITS
    antry
    0.73
    tnc
    0.71
    entimes
    0.69
    rone
    0.69
     cough
    0.69
     nursing
    0.69
    abeth
    0.67
    handle
    0.65
     deduct
    0.65
    allow
    0.63
    Activations Density 0.245%

    No Known Activations