© 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. 8-RES-JB
    11. 24324
    Prev
    Next
    INDEX
    Explanations

    instances where numerical references are made to small quantities

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "a few"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     agre
    -0.77
    andise
    -0.72
     conclud
    -0.72
    yrinth
    -0.70
    sein
    -0.69
    acus
    -0.69
    webkit
    -0.68
    venture
    -0.67
    alam
    -0.66
     thence
    -0.65
    POSITIVE LOGITS
     hundred
    1.55
     dozen
    1.53
     thousand
    1.36
     weeks
    1.17
     minutes
    1.05
     months
    1.05
     days
    1.04
    dozen
    1.03
     moments
    1.02
     nights
    0.98
    Activations Density 0.062%

    No Known Activations