© 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. 31728
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or implications

    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
    8
    +0.12
    0.6%
    512
    +0.12
    0.5%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.12
    0.04
    155
    +0.12
    0.04
    236
    +0.10
    0.04
    Negative Logits
    ItemTracker
    -0.73
    ocobo
    -0.72
    atech
    -0.71
     suspic
    -0.70
    @#&
    -0.68
    imore
    -0.68
    ovember
    -0.67
    thumbnails
    -0.65
    iazep
    -0.65
    itation
    -0.65
    POSITIVE LOGITS
     goodbye
    1.07
     we
    0.99
     nothing
    0.98
     fewer
    0.96
     they
    0.93
     you
    0.92
     nobody
    0.90
     there
    0.88
     lots
    0.79
     less
    0.79
    Activations Density 0.126%

    No Known Activations