© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29817
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating absence

    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
    373
    +0.20
    0.9%
    241
    +0.12
    0.5%
    100
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.20
    0.02
    360
    +0.12
    0.02
    183
    +0.12
    0.02
    Negative Logits
    çĶŁ
    -0.70
    ç·
    -0.69
     pockets
    -0.67
    å¦
    -0.65
    éģ
    -0.62
    æĸ
    -0.62
    ä¿
    -0.61
    warts
    -0.60
     NUM
    -0.59
    wart
    -0.58
    POSITIVE LOGITS
    ifications
    1.03
    eworthy
    1.01
    ify
    1.00
    ices
    0.98
    ification
    0.97
    withstanding
    0.95
    orious
    0.89
     Applic
    0.86
    epad
    0.84
    ified
    0.79
    Activations Density 0.062%

    No Known Activations