© 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. 2-RES-JB
    11. 15487
    Prev
    Next
    INDEX
    Explanations

    commands related to computer programming and software installation

    oai_token-act-pair · gpt-3.5-turbo

    technical commands and instructions related to software installation and system configuration

    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
     Flavoring
    -0.79
    AAA
    -0.77
    ¥µ
    -0.73
    EVA
    -0.72
    Ò
    -0.72
    hra
    -0.70
    îĢ
    -0.70
    ãĤª
    -0.70
    etsy
    -0.68
    Buyable
    -0.67
    POSITIVE LOGITS
     ~/.
    0.99
     filesystem
    0.97
     upstream
    0.96
    fs
    0.92
     ~/
    0.89
     gcc
    0.88
     foo
    0.88
     ssh
    0.85
    config
    0.84
     sudo
    0.82
    Activations Density 0.348%

    No Known Activations