© 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. 10-RES-JB
    11. 20573
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and software development processes

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming, dependencies, and installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mour
    -0.69
    bent
    -0.68
     Hanson
    -0.67
    ãĥ©ãĥ³
    -0.66
     Hilton
    -0.64
    waters
    -0.63
    quarters
    -0.62
     commemor
    -0.60
     stakes
    -0.60
    drug
    -0.60
    POSITIVE LOGITS
     dynamically
    1.26
     statically
    1.18
     manually
    1.17
     automatically
    1.17
     GUI
    1.13
     API
    1.10
    ¶
    1.10
     plugins
    1.09
     plugin
    1.08
     configure
    1.05
    Activations Density 0.312%

    No Known Activations