© 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. 4-RES-JB
    11. 10392
    Prev
    Next
    INDEX
    Explanations

    individual words or phrases that mention marks left on objects or people

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of marks or indicators

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

    No Comments

    Negative Logits
    ILLE
    -0.80
    æ©Ł
    -0.79
    ettel
    -0.67
    SOURCE
    -0.66
     tides
    -0.64
    imation
    -0.64
    UTION
    -0.62
    ctory
    -0.61
    ECD
    -0.61
     innings
    -0.61
    POSITIVE LOGITS
    manship
    1.47
    marks
    1.01
    emark
    0.95
     marks
    0.85
    mark
    0.84
    pelled
    0.83
    prints
    0.82
    terday
    0.80
    ovi
    0.80
    eting
    0.80
    Activations Density 0.019%

    No Known Activations