© 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. 27092
    Prev
    Next
    INDEX
    Explanations

    phrases describing familial relationships and childhood experiences

    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
    314
    +0.13
    0.6%
    105
    +0.11
    0.5%
    766
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.13
    0.15
    328
    +0.11
    0.09
    159
    +0.11
    0.10
    Negative Logits
     Clapper
    -0.74
    Invalid
    -0.70
     Heads
    -0.70
     Doomsday
    -0.69
     idiots
    -0.67
    heads
    -0.67
     fools
    -0.67
     Thumbnails
    -0.65
     JUSTICE
    -0.65
     Yesterday
    -0.65
    POSITIVE LOGITS
     stint
    1.20
     apprentices
    1.02
     upbringing
    0.96
     internship
    0.94
     career
    0.93
     vocational
    0.88
     lifelong
    0.87
     convent
    0.87
     boyfriend
    0.86
    unts
    0.85
    Activations Density 0.830%

    No Known Activations