© 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. 6574
    Prev
    Next
    INDEX
    Explanations

    words related to digital technology, specifically with the prefix "Sh" followed by a number in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the string "Sh" in various contexts

    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
     induct
    -0.73
     induction
    -0.73
     refere
    -0.70
     adjective
    -0.69
     eas
    -0.67
     corpus
    -0.66
     affection
    -0.65
    eur
    -0.65
     accus
    -0.64
     verb
    -0.64
    POSITIVE LOGITS
    Sh
    3.48
     Sh
    2.04
    sh
    1.98
    SH
    1.92
    Shar
    1.55
     sh
    1.50
     SH
    1.48
    SHA
    1.47
    Sham
    1.31
    Shin
    1.31
    Activations Density 0.012%

    No Known Activations