© 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 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. 9-RES-JB
    11. 2298
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest excess, exaggeration, or criticism

    oai_token-act-pair · gpt-3.5-turbo

    references to excessive or over-the-top situations or items

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.81
     Juliet
    -0.70
     Ranger
    -0.68
    itaire
    -0.68
     Bravo
    -0.67
     Bits
    -0.65
     Gazette
    -0.62
     WD
    -0.62
     Cassidy
    -0.62
     Doe
    -0.60
    POSITIVE LOGITS
    arching
    1.08
    represented
    1.08
    sized
    1.08
    whelming
    1.07
    emphasis
    1.07
    priced
    1.07
    performing
    1.06
    ealous
    1.02
    educated
    1.01
    regulated
    1.00
    Activations Density 0.027%

    No Known Activations