© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    expressions of mathematical functions and statistical metrics

    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
    314
    +0.17
    0.8%
    160
    +0.16
    0.7%
    479
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.17
    0.12
    107
    +0.16
    0.08
    314
    +0.15
    0.02
    Negative Logits
     trump
    -0.83
     annex
    -0.83
     favor
    -0.82
     exper
    -0.82
     lim
    -0.81
     bonding
    -0.80
     pudding
    -0.80
     cher
    -0.79
     elf
    -0.78
     poaching
    -0.77
    POSITIVE LOGITS
    Un
    1.61
    Sem
    1.61
    Pers
    1.60
    Double
    1.60
    Ass
    1.59
    Re
    1.59
    D
    1.59
    E
    1.58
    Int
    1.58
    R
    1.58
    Activations Density 0.527%

    No Known Activations