© 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. 2-RES-JB
    11. 17231
    Prev
    Next
    INDEX
    Explanations

    words related to programming languages and syntax

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "io" in various contexts, particularly in code or programming references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holder
    -0.70
     quarters
    -0.70
     thieves
    -0.69
    ancies
    -0.69
     poppy
    -0.68
     Shattered
    -0.66
     Shades
    -0.66
     embodiments
    -0.65
    puter
    -0.65
    OWS
    -0.61
    POSITIVE LOGITS
    ppo
    1.28
    io
    1.09
    ption
    1.08
    cean
    1.04
    zzi
    1.02
    ichi
    0.99
    ctl
    0.99
    ius
    0.97
    ppe
    0.95
    zza
    0.94
    Activations Density 0.014%

    No Known Activations