© 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. 10-RES-JB
    11. 10472
    Prev
    Next
    INDEX
    Explanations

    forms of personal names or references to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    symbols, abbreviations, and numerical references typically associated with metadata or citations

    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
     Garfield
    -0.88
     Holden
    -0.88
     Garner
    -0.86
     DAR
    -0.84
     Irwin
    -0.83
     Hayden
    -0.82
     STE
    -0.82
     Sheridan
    -0.80
     Henri
    -0.79
     gir
    -0.77
    POSITIVE LOGITS
    om
    1.39
    oms
    1.33
    omy
    1.18
    oma
    1.12
    pl
    1.12
    OM
    1.11
    olia
    1.11
    ombs
    1.10
    omes
    1.10
    omed
    1.09
    Activations Density 0.269%

    No Known Activations