© 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. 31365
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities related to voting or ratings

    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
    196
    +0.10
    0.4%
    141
    +0.10
    0.4%
    717
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.15
    160
    +0.10
    0.15
    102
    +0.10
    0.12
    Negative Logits
    anwhile
    -0.61
    elta
    -0.60
    oing
    -0.59
    apters
    -0.59
     finer
    -0.59
     insertion
    -0.58
     contagious
    -0.58
     grooming
    -0.58
    enture
    -0.58
    roup
    -0.56
    POSITIVE LOGITS
    Answer
    2.13
     Answer
    1.56
    Absolutely
    1.46
    Well
    1.36
    Yes
    1.33
    YES
    1.26
     answer
    1.25
    answer
    1.22
     Nope
    1.18
    Probably
    1.12
    Activations Density 0.646%

    No Known Activations