© 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. 20584
    Prev
    Next
    INDEX
    Explanations

    references to the technology term "Unity" and its related context, such as events, versions, and distributions

    oai_token-act-pair · gpt-3.5-turbo

    references to software development milestones and key events

    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
     Harlem
    -0.87
     Guerrero
    -0.87
    steen
    -0.87
     bowling
    -0.86
     Pradesh
    -0.83
    hattan
    -0.80
     stim
    -0.78
    agara
    -0.78
    Michigan
    -0.76
     Booker
    -0.76
    POSITIVE LOGITS
     Ubuntu
    2.18
     Debian
    1.99
     Fedora
    1.97
     CentOS
    1.87
     Linux
    1.86
     KDE
    1.84
     GNOME
    1.79
     debian
    1.72
    Linux
    1.72
    ubuntu
    1.70
    Activations Density 0.210%

    No Known Activations