© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24085
    Prev
    Next
    INDEX
    Explanations

    C++ programming syntax involving namespaces and pointers

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs and syntax related to code definitions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     borne
    -0.78
     streaks
    -0.76
     dared
    -0.74
     wise
    -0.74
     thrill
    -0.74
     bursts
    -0.72
     shooters
    -0.72
     buzz
    -0.71
     footage
    -0.71
     tabloid
    -0.71
    POSITIVE LOGITS
    Create
    1.34
    Init
    1.30
    Generic
    1.29
    Static
    1.29
    Simple
    1.27
    AUT
    1.26
    Internal
    1.25
    Private
    1.24
    Default
    1.24
    Auto
    1.24
    Activations Density 0.117%

    No Known Activations