© 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. 18825
    Prev
    Next
    INDEX
    Explanations

    the word "One" that signifies a new topic or point being introduced

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "One."

    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
     fortune
    -0.67
     reserves
    -0.63
     respectively
    -0.60
     jun
    -0.60
     compet
    -0.59
     stricken
    -0.58
     circ
    -0.58
     corrections
    -0.58
     capit
    -0.57
     disappro
    -0.56
    POSITIVE LOGITS
    One
    3.06
     One
    2.07
    Another
    1.90
    Two
    1.85
    one
    1.65
    Three
    1.59
    Among
    1.59
    Many
    1.57
    Four
    1.55
    ONE
    1.50
    Activations Density 0.018%

    No Known Activations