© 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. 6-RES-JB
    11. 13597
    Prev
    Next
    INDEX
    Explanations

    verbing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "few."

    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
    acus
    -0.86
    roit
    -0.77
    hes
    -0.74
    yrinth
    -0.73
    abal
    -0.72
    webkit
    -0.72
    UAL
    -0.71
    sein
    -0.69
    alam
    -0.68
    said
    -0.68
    POSITIVE LOGITS
     dozen
    1.36
     hundred
    1.25
     thousand
    1.07
     weeks
    1.00
    dozen
    0.95
     months
    0.90
     days
    0.89
     nights
    0.88
     minutes
    0.86
     exceptions
    0.84
    Activations Density 0.048%

    No Known Activations