© 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. 3682
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms related to coding functions and operations

    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
    321
    +0.13
    0.6%
    532
    +0.11
    0.5%
    291
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.02
    158
    +0.11
    0.01
    326
    +0.11
    0.01
    Negative Logits
    enegger
    -1.16
     Wonders
    -0.70
    clerosis
    -0.69
     swall
    -0.67
    Ô
    -0.65
     Wem
    -0.64
     seams
    -0.64
     Mellon
    -0.63
     STEP
    -0.63
    eatures
    -0.63
    POSITIVE LOGITS
    onen
    0.83
    accompan
    0.76
    ciating
    0.74
    oyal
    0.73
    attach
    0.68
     litter
    0.66
    agne
    0.63
     thanking
    0.63
    bil
    0.62
    dump
    0.60
    Activations Density 0.055%

    No Known Activations