Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23381
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end of sentences represented by periods

    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
     drip
    -0.57
     dots
    -0.57
     Thomas
    -0.56
     toddler
    -0.51
     click
    -0.50
    Hamilton
    -0.50
     kitten
    -0.50
     Spurs
    -0.49
     Seahawks
    -0.49
     pots
    -0.49
    POSITIVE LOGITS
    .[
    3.62
    ".[
    3.22
    ."[
    3.17
    ).[
    3.08
    ,[
    2.99
    :[
    2.39
    [/
    2.18
    )[
    2.15
    .]
    2.05
     [/
    1.94
    Activations Density 0.034%

    No Known Activations