© 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. 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. 2351
    Prev
    Next
    INDEX
    Explanations

    fragments starting with special characters indicating some kind of formatting or structure

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     RAF
    -0.67
     QC
    -0.64
     RAID
    -0.62
     jog
    -0.61
     Windsor
    -0.61
     Bermuda
    -0.60
     Siem
    -0.60
     Gaul
    -0.60
     Orchestra
    -0.59
     Drawn
    -0.58
    POSITIVE LOGITS
    egal
    1.00
    ï¸ı
    0.98
    own
    0.86
    same
    0.83
    agree
    0.79
    river
    0.77
    ebook
    0.77
    owed
    0.74
    rain
    0.73
    ross
    0.73
    Activations Density 0.293%

    No Known Activations