© 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. 6-RES-JB
    11. 9201
    Prev
    Next
    INDEX
    Explanations

    specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    specific pieces of quantitative data and key proper nouns

    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
     paraph
    -0.52
     Retrieved
    -0.52
     catalogue
    -0.50
     contagious
    -0.50
     booklet
    -0.50
     Stard
    -0.50
     '[
    -0.47
     acronym
    -0.47
    Downloadha
    -0.47
     likened
    -0.47
    POSITIVE LOGITS
    itto
    0.66
    +.
    0.59
     ..........
    0.57
    OPE
    0.56
    addy
    0.56
    +,
    0.55
    ample
    0.55
    ":{"
    0.55
    brids
    0.54
    /.
    0.54
    Activations Density 1.054%

    No Known Activations