© 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. 11-RES-JB
    11. 2833
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating likelihood or expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert expectations or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CI
    -0.67
     Patty
    -0.62
     Afgh
    -0.57
     Rox
    -0.57
     Cir
    -0.56
     Mehran
    -0.56
    yss
    -0.54
     Ends
    -0.54
     Fra
    -0.54
    HER
    -0.54
    POSITIVE LOGITS
     ideally
    1.15
    ered
    1.11
     be
    1.09
    ering
    1.04
     suffice
    1.04
     theoretically
    0.93
    nt
    0.93
     NEVER
    0.89
     beware
    0.87
     definitely
    0.86
    Activations Density 0.068%

    No Known Activations