© 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. 9-RES-JB
    11. 1625
    Prev
    Next
    INDEX
    Explanations

    the phrase "more than a" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons or quantities involving "more than a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nanto
    -0.80
    ulhu
    -0.74
    ONEY
    -0.68
     Dynamics
    -0.67
    ãĥ´
    -0.66
    mobi
    -0.65
    sbm
    -0.65
    ornia
    -0.63
    ãĤ´
    -0.63
     Volunte
    -0.61
    POSITIVE LOGITS
     dozen
    1.04
    dozen
    0.93
     hundred
    0.82
     thousand
    0.80
     decade
    0.78
     whiff
    0.77
    volent
    0.74
    ĪĴ
    0.73
    cknowled
    0.72
     symbolic
    0.71
    Activations Density 0.065%

    No Known Activations