© 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. 647
    Prev
    Next
    INDEX
    Explanations

    unusual characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters representing non-standard formatting or encoding issues

    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
    enegger
    -1.06
     Nanto
    -0.78
    ãģ®éŃĶ
    -0.67
    anwhile
    -0.67
    manship
    -0.65
     visitor
    -0.64
     Sidd
    -0.64
    iants
    -0.63
     Som
    -0.63
     Alchemist
    -0.62
    POSITIVE LOGITS
    ´
    1.54
    ³
    1.52
    ¿
    1.48
    ¦
    1.44
    ¹
    1.43
    ¨
    1.42
    ¼
    1.40
    ¤
    1.37
    º
    1.35
    Ĵ
    1.35
    Activations Density 0.015%

    No Known Activations