© 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. 1-RES-JB
    11. 5063
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" used as an intensifier

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ropolitan
    -0.65
    wreck
    -0.65
     glances
    -0.61
     cradle
    -0.58
    idity
    -0.57
     Dive
    -0.57
     acre
    -0.57
    haven
    -0.54
     disbelief
    -0.54
     arrival
    -0.54
    POSITIVE LOGITS
    bered
    1.13
    oths
    1.10
    oooo
    1.03
    othes
    1.01
    othe
    1.00
    ooo
    1.00
    apy
    0.98
    zin
    0.97
    oooooooo
    0.95
    oooooooooooooooo
    0.93
    Activations Density 0.093%

    No Known Activations