© 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. 0-RES-JB
    11. 11307
    Prev
    Next
    INDEX
    Explanations

    fingerprints, especially when mentioned in relation to investigation or identification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fingerprints and gloss, often in contexts discussing identity or impression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bre
    -0.78
     carriage
    -0.78
    Mas
    -0.73
     Glou
    -0.73
     sidx
    -0.72
    rf
    -0.70
    Sir
    -0.69
    abetic
    -0.69
    thur
    -0.68
     Albion
    -0.68
    POSITIVE LOGITS
     fingerprints
    1.77
     ré
    1.59
     gloss
    1.57
     Photoshop
    1.34
     Salvador
    1.24
     Gloss
    1.11
     primer
    1.08
     Dawson
    1.07
     critique
    1.06
     beneficiaries
    0.99
    Activations Density 0.064%

    No Known Activations