© 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. 31334
    Prev
    Next
    INDEX
    Explanations

    the word "not" in various contexts

    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
    314
    +0.11
    0.5%
    622
    +0.11
    0.5%
    596
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.11
    0.02
    406
    +0.11
    0.02
    404
    +0.10
    0.02
    Negative Logits
    SOURCE
    -0.75
     Boat
    -0.63
     proportions
    -0.61
    à¥
    -0.61
    HAM
    -0.60
    ONSORED
    -0.58
    vier
    -0.58
     destro
    -0.57
     misunder
    -0.55
     motives
    -0.55
    POSITIVE LOGITS
    tery
    1.24
    ting
    1.20
    rans
    1.08
    assium
    1.05
    eca
    1.00
    opia
    0.97
    opic
    0.92
    hered
    0.91
    ty
    0.91
    ential
    0.90
    Activations Density 0.157%

    No Known Activations