© 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 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. 3-RES-JB
    11. 20289
    Prev
    Next
    INDEX
    Explanations

    commands and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and commands related to programming and software installation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.78
     funer
    -0.76
     Weeks
    -0.72
     Izan
    -0.71
     Korra
    -0.70
     Kara
    -0.70
     Friendship
    -0.69
    cffffcc
    -0.69
     Vict
    -0.67
     Breath
    -0.67
    POSITIVE LOGITS
    utils
    1.05
    fs
    0.98
    utable
    0.98
    plugin
    0.97
    db
    0.96
     plugin
    0.93
    Config
    0.92
    fw
    0.92
    Debug
    0.91
    Desktop
    0.91
    Activations Density 0.314%

    No Known Activations