© 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. 8-RES_POST_32K-OAI
    11. 8059
    Prev
    Next
    INDEX
    Explanations

    articles indicating either singular or plural nouns

    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
    355
    +0.12
    0.5%
    374
    +0.11
    0.5%
    706
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.14
    362
    +0.11
    0.08
    328
    +0.11
    0.06
    Negative Logits
    allion
    -0.69
     Horizons
    -0.66
    iciency
    -0.66
    yss
    -0.65
    erella
    -0.64
    iversary
    -0.63
    orsi
    -0.63
    irts
    -0.62
    hirt
    -0.62
    redit
    -0.61
    POSITIVE LOGITS
     nutshell
    1.25
     hurry
    1.24
     manner
    1.18
     context
    0.99
     guise
    0.98
     vein
    0.91
     vain
    0.91
     contexts
    0.89
     crowded
    0.85
     fashion
    0.85
    Activations Density 0.274%

    No Known Activations