© 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. 9-RES-JB
    11. 20310
    Prev
    Next
    INDEX
    Explanations

    file names and software-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to programming concepts and tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kahn
    -0.88
     Ninth
    -0.88
     Shank
    -0.87
     Hayden
    -0.84
     Grimm
    -0.84
     Chong
    -0.84
     Lon
    -0.83
     Gong
    -0.82
     Pai
    -0.82
     Schne
    -0.81
    POSITIVE LOGITS
    ctl
    1.31
    utils
    1.30
    info
    1.19
    cli
    1.16
    plugin
    1.15
    rc
    1.14
    _
    1.13
    tools
    1.11
    wrapper
    1.10
    plugins
    1.08
    Activations Density 0.245%

    No Known Activations