© 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. 6-RES-JB
    11. 10643
    Prev
    Next
    INDEX
    Explanations

    statements about official documents and records

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authorship or attribution in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.65
    mercial
    -0.65
    luster
    -0.64
    effic
    -0.63
    ornings
    -0.63
    ploy
    -0.61
    south
    -0.59
    amina
    -0.59
    quartered
    -0.58
    heastern
    -0.55
    POSITIVE LOGITS
     guiActive
    0.66
     titled
    0.62
     url
    0.60
    çīĪ
    0.60
     {*
    0.59
     explanatory
    0.58
     annotations
    0.56
     parentheses
    0.55
     aloud
    0.55
     crochet
    0.54
    Activations Density 1.479%

    No Known Activations