© 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. 9-RES-JB
    11. 3783
    Prev
    Next
    INDEX
    Explanations

    written expressions of percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo
    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
    ↵Âł
    -0.71
     atroc
    -0.68
    ³³³³³³³³
    -0.63
     Trotsky
    -0.62
     ³³
    -0.62
     whilst
    -0.60
    `.
    -0.60
     damned
    -0.60
    Terror
    -0.60
     consequ
    -0.59
    POSITIVE LOGITS
    eele
    0.73
    Enlarge
    0.73
     marketers
    0.71
     Kickstarter
    0.69
     Lyft
    0.67
     Tinder
    0.64
     nonprofits
    0.63
     millennials
    0.63
     marketing
    0.62
    Poké
    0.62
    Activations Density 1.745%

    No Known Activations