© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 12993
    Prev
    Next
    INDEX
    Explanations

    comma characters in a list

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or commas used in a variety of contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    soever
    -0.69
     behavi
    -0.67
     hemor
    -0.63
     âĵĺ
    -0.62
     antioxid
    -0.61
     opin
    -0.60
    enhagen
    -0.58
     behav
    -0.56
     streng
    -0.56
     newsp
    -0.56
    POSITIVE LOGITS
    000
    1.61
    500
    1.17
    800
    1.12
    700
    1.12
    040
    1.11
    075
    1.11
    600
    1.09
    070
    1.08
    400
    1.05
    940
    1.04
    Activations Density 0.152%

    No Known Activations