© 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 EvalsExportsinterp-engineNEWAPI 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. 15219
    Prev
    Next
    INDEX
    Explanations

    sources and citations within text

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of sources

    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
    ney
    -0.72
    eq
    -0.69
    itaire
    -0.68
    btn
    -0.65
     Disorder
    -0.64
    reciation
    -0.64
    case
    -0.63
    eeee
    -0.62
    achine
    -0.61
    olon
    -0.61
    POSITIVE LOGITS
     sources
    4.02
     Sources
    3.03
    Sources
    2.65
     source
    2.56
    ources
    2.30
    source
    2.00
     sourcing
    1.69
     Source
    1.53
     suppliers
    1.50
     insiders
    1.49
    Activations Density 0.013%

    No Known Activations