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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23634
    Prev
    Next
    INDEX
    Explanations

    text related to document introductions

    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 @ 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
     pick
    -0.74
     ticket
    -0.69
     bounced
    -0.68
    aters
    -0.66
     cra
    -0.66
     wild
    -0.66
     bidder
    -0.65
     hit
    -0.65
     ward
    -0.65
     squad
    -0.65
    POSITIVE LOGITS
    Introduction
    3.81
     Introduction
    2.75
    Overview
    2.10
    Description
    1.86
    Abstract
    1.64
    Background
    1.61
     Intro
    1.48
    Synopsis
    1.48
    Introdu
    1.48
    ODUCT
    1.44
    Activations Density 0.037%

    No Known Activations