© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17073
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to documentation and information sharing, such as "policy background," "document overview," and "installation."

    oai_token-act-pair · gpt-3.5-turbo

    fragments of text or sections related to various topics or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attled
    -0.71
    ously
    -0.65
    feld
    -0.65
    ivably
    -0.63
    equal
    -0.60
     dared
    -0.60
    Brit
    -0.59
     texted
    -0.59
     Farrell
    -0.59
    boats
    -0.59
    POSITIVE LOGITS
     Definitions
    1.18
    Overview
    1.15
     Overview
    1.09
     Introduction
    0.98
     Basics
    0.96
    Introduction
    0.93
     Summary
    0.92
     Background
    0.92
     nutshell
    0.91
     basics
    0.89
    Activations Density 0.909%

    No Known Activations