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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19990
    Prev
    Next
    INDEX
    Explanations

    keywords related to introductory topics or chapters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Introduction"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    oned
    -0.70
    eez
    -0.66
     mouths
    -0.66
    lo
    -0.65
     Dare
    -0.65
    oning
    -0.64
    ipping
    -0.62
     corners
    -0.62
     hire
    -0.62
    pler
    -0.61
    POSITIVE LOGITS
    Introduction
    1.14
     Introduction
    1.09
    xual
    1.07
    Analysis
    0.91
     Overview
    0.85
    Overview
    0.84
     Presence
    0.83
    ¶
    0.81
     Basics
    0.81
    insula
    0.79
    Activations Density 0.017%

    No Known Activations