© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    references to sequences or notable first occurrences

    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
    756
    +0.13
    0.6%
    66
    +0.13
    0.6%
    554
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.13
    0.07
    718
    +0.13
    0.04
    756
    +0.11
    0.05
    Negative Logits
    rings
    -0.82
    iasis
    -0.80
    ress
    -0.80
    olls
    -0.77
    roud
    -0.75
    ugar
    -0.73
    ahs
    -0.73
    olina
    -0.72
    rina
    -0.71
    ocracy
    -0.71
    POSITIVE LOGITS
     conclud
    0.81
    theless
    0.75
     advent
    0.74
     departure
    0.70
     tremend
    0.68
     eleph
    0.67
     embark
    0.66
     amen
    0.65
     deferred
    0.64
     arrival
    0.64
    Activations Density 1.742%

    No Known Activations