© 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. 27232
    Prev
    Next
    INDEX
    Explanations

    references to personal care and cosmetic products

    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
    738
    +0.11
    0.5%
    595
    +0.11
    0.5%
    275
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.06
    288
    +0.11
    0.08
    40
    +0.10
    0.06
    Negative Logits
    £ı
    -0.88
    é¾
    -0.80
    CLASSIFIED
    -0.76
    cephal
    -0.73
    bda
    -0.71
    76561
    -0.69
    ajor
    -0.69
    «ĺ
    -0.69
    lvl
    -0.67
    erial
    -0.67
    POSITIVE LOGITS
     applic
    1.16
     capsules
    1.05
     refill
    1.02
     disinfect
    0.98
     additives
    0.96
     wipes
    0.95
     soaked
    0.95
     dispens
    0.94
     formulations
    0.94
     shampoo
    0.94
    Activations Density 0.569%

    No Known Activations