© 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. 7-RES-JB
    11. 21817
    Prev
    Next
    INDEX
    Explanations

    some specific technical terms and commands related to programming

    oai_token-act-pair · gpt-3.5-turbo

    file types and programming-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patron
    -0.83
     Disorder
    -0.83
     Flavoring
    -0.81
     Referred
    -0.79
     Cous
    -0.79
     Fas
    -0.78
     Aires
    -0.77
     Dise
    -0.77
     Leban
    -0.76
     Seasons
    -0.75
    POSITIVE LOGITS
    ascript
    1.04
    pd
    1.02
    cs
    0.96
    cd
    0.95
    df
    0.92
    wd
    0.91
    drm
    0.91
    rc
    0.91
    admin
    0.89
    ml
    0.88
    Activations Density 0.125%

    No Known Activations