© 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. 11164
    Prev
    Next
    INDEX
    Explanations

    instances of contractions, specifically the contraction "won't"

    oai_token-act-pair · gpt-3.5-turbo

    the expression of negation, particularly focusing on the word "won't."

    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
    gypt
    -0.61
     agg
    -0.60
     practicable
    -0.59
     constrained
    -0.58
     princ
    -0.58
     anat
    -0.58
     bonded
    -0.58
     discontinued
    -0.57
     entertained
    -0.56
     populated
    -0.56
    POSITIVE LOGITS
    't
    1.78
    now
    1.14
    cest
    1.10
    itive
    1.07
    kish
    1.01
    kered
    0.96
    ky
    0.93
    ipeg
    0.93
    ks
    0.91
    etsk
    0.91
    Activations Density 0.034%

    No Known Activations