© 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. 4-RES-JB
    11. 20507
    Prev
    Next
    INDEX
    Explanations

    file paths or commands in a computer programming context

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming and software components

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

    No Comments

    Negative Logits
     Therapy
    -0.83
     Friendship
    -0.82
     Weeks
    -0.79
     Charity
    -0.77
     Chance
    -0.74
     Seasons
    -0.74
     Lot
    -0.74
     Cotton
    -0.71
     ANG
    -0.71
     Principle
    -0.71
    POSITIVE LOGITS
    args
    1.00
    utils
    0.97
    admin
    0.94
    plugin
    0.94
    fw
    0.93
    ql
    0.93
    df
    0.92
    ctl
    0.91
    ify
    0.91
    callback
    0.91
    Activations Density 0.212%

    No Known Activations