© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" used in contrastive statements

    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
    ento
    -0.74
    bia
    -0.69
     Horizons
    -0.66
     Dreams
    -0.66
    oire
    -0.64
     Combine
    -0.63
     Europa
    -0.63
     Skies
    -0.63
    eatures
    -0.63
    OPLE
    -0.62
    POSITIVE LOGITS
     nonetheless
    1.16
     nevertheless
    1.15
    chery
    1.13
     unmist
    1.03
     persistent
    0.99
     effective
    0.97
     undeniably
    0.94
     undeniable
    0.90
     deadly
    0.89
     still
    0.89
    Activations Density 0.052%

    No Known Activations