© 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. 1-RES-JB
    11. 14525
    Prev
    Next
    INDEX
    Explanations

    descriptions of various entities

    oai_token-act-pair · gpt-3.5-turbo

    various instances of the word "Description" within the document

    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
     flux
    -0.82
    zig
    -0.79
     brainstorm
    -0.74
     labour
    -0.71
     labor
    -0.69
     booster
    -0.65
    åĤ
    -0.65
     wool
    -0.65
    bos
    -0.64
     prayer
    -0.64
    POSITIVE LOGITS
    Description
    1.68
     Description
    1.01
    Features
    1.01
    isine
    0.98
    CRIPTION
    0.98
     Mehran
    0.93
    Overview
    0.88
     Installation
    0.86
     Seym
    0.85
     Specifications
    0.84
    Activations Density 0.031%

    No Known Activations