© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 11303
    Prev
    Next
    INDEX
    Explanations

    instances where the word "In" is capitalized and followed by some content that follows a specific structure or template

    oai_token-act-pair · gpt-3.5-turbo

    the word "In" at the beginning of various statements or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ages
    -0.67
     pudding
    -0.66
     goodbye
    -0.65
     yes
    -0.65
     mouths
    -0.64
     stra
    -0.64
     fuck
    -0.64
     plat
    -0.64
     swe
    -0.63
     smooth
    -0.63
    POSITIVE LOGITS
    In
    2.63
    During
    1.98
    On
    1.86
    According
    1.80
    When
    1.79
    Through
    1.78
    After
    1.76
    At
    1.75
    ccording
    1.75
    Since
    1.74
    Activations Density 0.067%

    No Known Activations