© 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. 1-RES-JB
    11. 3719
    Prev
    Next
    INDEX
    Explanations

    words related to problematic situations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "add" or related phrases indicating accumulation or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rip
    -0.77
     Trees
    -0.71
     SPI
    -0.71
    externalActionCode
    -0.68
     Seraph
    -0.67
     Fi
    -0.66
     departure
    -0.65
     Borders
    -0.65
     Bos
    -0.64
     Baltic
    -0.64
    POSITIVE LOGITS
    add
    1.49
    itionally
    1.41
    itional
    1.26
    icted
    1.21
    ition
    1.10
    added
    1.06
    ressed
    1.04
    itions
    1.03
    icts
    1.01
    adding
    1.00
    Activations Density 0.007%

    No Known Activations