© 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. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29691
    Prev
    Next
    INDEX
    Explanations

    terms related to flu and other respiratory illnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    0
    +0.12
    0.6%
    211
    +0.11
    0.5%
    504
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.04
    314
    +0.11
    -0.01
    374
    +0.10
    -0.01
    Negative Logits
     Skydragon
    -0.82
    dain
    -0.76
     Worlds
    -0.74
    RAM
    -0.65
     landslide
    -0.60
     Rebirth
    -0.60
    eering
    -0.60
     Elven
    -0.59
     crabs
    -0.59
     Redemption
    -0.59
    POSITIVE LOGITS
    orescence
    1.38
    oresc
    1.36
    orescent
    1.21
    renheit
    0.96
    ency
    0.85
    kered
    0.83
    Mist
    0.82
    enza
    0.79
    ores
    0.78
    ornia
    0.77
    Activations Density 0.245%

    No Known Activations