© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 8332
    Prev
    Next
    INDEX
    Explanations

    phrases or references to articles and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    736
    +0.12
    0.5%
    765
    +0.10
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.11
    362
    +0.10
    0.07
    159
    +0.10
    0.05
    Negative Logits
    enance
    -0.75
     prevailed
    -0.72
    intendent
    -0.66
    mitter
    -0.63
     Colo
    -0.63
    wered
    -0.62
    arian
    -0.62
     reacts
    -0.62
     survives
    -0.61
    lambda
    -0.60
    POSITIVE LOGITS
     larger
    0.96
     broader
    0.96
     continuum
    0.91
     wider
    0.84
     trilogy
    0.77
     deepening
    0.76
    GoldMagikarp
    0.74
    series
    0.74
     trend
    0.73
    jong
    0.73
    Activations Density 0.448%

    No Known Activations