© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3520
    Prev
    Next
    INDEX
    Explanations

    information related to software availability and compatibility

    oai_token-act-pair · gpt-3.5-turbo

    references to software availability and compatibility across multiple platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nothing
    -0.83
    notice
    -0.74
    Ĭ±
    -0.69
    redd
    -0.69
     Hasan
    -0.67
     Daryl
    -0.67
     juven
    -0.67
    cffffcc
    -0.67
    sie
    -0.66
    ought
    -0.64
    POSITIVE LOGITS
     platforms
    1.68
     browsers
    1.61
     formats
    1.46
     languages
    1.41
     launchers
    1.30
     architectures
    1.27
     devices
    1.24
     flavours
    1.21
     operating
    1.19
     configurations
    1.19
    Activations Density 0.253%

    No Known Activations