© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 12929
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities where one is described as being more intense or significant than the other

    oai_token-act-pair · gpt-3.5-turbo

    the article "the" used in various contexts indicating comparisons

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     besides
    -0.76
    won
    -0.73
    ãĥ»
    -0.72
     followed
    -0.72
    amar
    -0.72
     ahead
    -0.72
     Became
    -0.70
    SPONSORED
    -0.70
     alike
    -0.70
     ********************************
    -0.66
    POSITIVE LOGITS
     rest
    1.28
     usual
    1.22
     aforementioned
    1.13
     proverbial
    1.10
     nearest
    1.08
     entirety
    1.08
     slightest
    1.08
     ones
    1.05
     original
    1.03
     originals
    1.01
    Activations Density 0.211%

    No Known Activations