© 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. 3448
    Prev
    Next
    INDEX
    Explanations

    concepts related to reduction, avoidance, and minimizing various issues

    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
    331
    +0.12
    0.5%
    406
    +0.11
    0.5%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.12
    0.07
    67
    +0.11
    0.06
    43
    +0.10
    0.04
    Negative Logits
     Druid
    -0.73
     Syri
    -0.71
     Palm
    -0.67
    Pal
    -0.66
     manifesto
    -0.66
     Gork
    -0.65
    Alias
    -0.65
     Jonah
    -0.64
     Longh
    -0.63
     Methodist
    -0.63
    POSITIVE LOGITS
    acco
    0.81
    zyme
    0.71
     CTR
    0.71
    comings
    0.70
     illnesses
    0.69
    encies
    0.69
    adish
    0.69
     Turing
    0.67
    ãĥīãĥ©
    0.67
    effic
    0.65
    Activations Density 1.878%

    No Known Activations