© 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. 0-RES-JB
    11. 13157
    Prev
    Next
    INDEX
    Explanations

    references to external sources or citations

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or citations

    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
     elevated
    -0.76
     sat
    -0.69
     repeated
    -0.68
     rode
    -0.67
     decre
    -0.65
     sustained
    -0.65
     kne
    -0.63
     st
    -0.63
     clut
    -0.63
     remod
    -0.63
    POSITIVE LOGITS
    source
    4.36
    ources
    2.06
    Source
    2.05
    SOURCE
    1.92
     source
    1.89
    ourced
    1.73
    Sources
    1.68
    ource
    1.65
     sources
    1.61
    src
    1.57
    Activations Density 0.015%

    No Known Activations