© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4073
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical information

    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
    481
    +0.17
    0.8%
    561
    +0.10
    0.5%
    745
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.17
    0.04
    739
    +0.10
    0.02
    569
    +0.10
    0.02
    Negative Logits
    mble
    -0.73
    netflix
    -0.71
    FOX
    -0.69
    pires
    -0.64
     autonom
    -0.64
     subconscious
    -0.63
    ihar
    -0.62
    gp
    -0.60
     downstream
    -0.60
     bloss
    -0.59
    POSITIVE LOGITS
     Edition
    0.71
    argon
    0.70
    á¸
    0.70
    lied
    0.68
     Legislation
    0.67
     Phar
    0.66
     Accountability
    0.66
     Chau
    0.65
     Repe
    0.64
     Accounts
    0.64
    Activations Density 0.407%

    No Known Activations