© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17473
    Prev
    Next
    INDEX
    Explanations

    years mentioned within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    the presence of parentheses in text, likely indicating titles or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prey
    -0.82
     retard
    -0.79
     faces
    -0.77
     clin
    -0.76
     crop
    -0.74
     administration
    -0.74
     physique
    -0.74
     crocod
    -0.73
     discrim
    -0.73
     swell
    -0.73
    POSITIVE LOGITS
    formerly
    1.83
    which
    1.67
    aka
    1.57
    pictured
    1.53
    2006
    1.48
    2003
    1.48
    2004
    1.47
    also
    1.47
    1993
    1.47
    1998
    1.46
    Activations Density 0.105%

    No Known Activations