© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "few" indicating scarcity or rarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express rarity or infrequency

    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
     forward
    -0.66
     arch
    -0.63
     into
    -0.63
     submission
    -0.63
     originally
    -0.63
     affiliated
    -0.63
     stuff
    -0.62
     shell
    -0.62
     outlet
    -0.62
     pitch
    -0.62
    POSITIVE LOGITS
     Few
    3.63
    Few
    2.50
    few
    2.01
     Less
    1.24
     Many
    1.22
     few
    1.22
     Worse
    1.14
     Several
    1.05
     Often
    1.02
    Less
    1.01
    Activations Density 0.009%

    No Known Activations