© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    references to paternal figures and their influence or impact

    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
    394
    +0.13
    0.6%
    585
    +0.12
    0.5%
    428
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.13
    0.03
    659
    +0.12
    0.03
    24
    +0.11
    0.02
    Negative Logits
    bats
    -0.77
    ohm
    -0.73
    sbm
    -0.73
    reality
    -0.70
    ogyn
    -0.69
    archment
    -0.68
    vision
    -0.68
    ova
    -0.67
    mint
    -0.67
    kees
    -0.65
    POSITIVE LOGITS
     Himself
    0.71
     DK
    0.69
     ben
    0.65
     Slim
    0.65
     Morty
    0.64
     erection
    0.59
     evangelicals
    0.59
    volent
    0.59
     Trog
    0.59
     congregation
    0.58
    Activations Density 0.349%

    No Known Activations