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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31300
    Prev
    Next
    INDEX
    Explanations

    mentions of sleep and sleep-related issues

    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
    575
    +0.14
    0.6%
    314
    +0.10
    0.5%
    416
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.03
    125
    +0.10
    0.02
    325
    +0.10
    0.02
    Negative Logits
     Manson
    -0.73
    xus
    -0.71
     Mehran
    -0.69
     Kushner
    -0.69
    vous
    -0.66
     Unicode
    -0.64
     Hebdo
    -0.63
    folios
    -0.63
     Hodg
    -0.59
     Fleming
    -0.59
    POSITIVE LOGITS
    walking
    1.35
     deprivation
    1.29
     deprived
    1.10
    iness
    1.06
    overs
    1.04
    walk
    1.03
    walker
    1.03
    dep
    0.98
    wear
    0.94
    wake
    0.93
    Activations Density 0.105%

    No Known Activations