© 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. 27278
    Prev
    Next
    INDEX
    Explanations

    numerical values related to quantities or measurements

    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
    63
    +0.13
    0.6%
    760
    +0.12
    0.5%
    674
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.13
    0.05
    260
    +0.12
    0.06
    471
    +0.10
    0.05
    Negative Logits
    itely
    -0.78
    venge
    -0.74
    ifice
    -0.73
    terness
    -0.73
    krit
    -0.72
    hower
    -0.70
    pport
    -0.69
    ufact
    -0.69
    ription
    -0.68
    ļéĨĴ
    -0.67
    POSITIVE LOGITS
    +
    1.18
     volts
    0.96
    +.
    0.96
     miles
    0.92
     sq
    0.91
     yen
    0.90
    aires
    0.90
     lbs
    0.89
     pounds
    0.87
    ths
    0.86
    Activations Density 0.254%

    No Known Activations