© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15941
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and measurements related to electronics or computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artisan
    -0.71
     accessibility
    -0.66
     crunch
    -0.64
    ĸļ
    -0.62
    earchers
    -0.61
     supervisor
    -0.61
    reau
    -0.60
    isexual
    -0.60
     chew
    -0.60
     specialization
    -0.60
    POSITIVE LOGITS
    MSN
    1.20
     Rated
    0.76
     Oops
    0.67
    XM
    0.67
     Fahrenheit
    0.66
    INS
    0.66
    coins
    0.62
    acht
    0.61
    phot
    0.61
    Catalog
    0.61
    Activations Density 0.286%

    No Known Activations