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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1761
    Prev
    Next
    INDEX
    Explanations

    commands or instructions starting with "First,"

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases or transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abled
    -0.75
    driving
    -0.72
    rams
    -0.72
    oslav
    -0.71
    nes
    -0.70
    ildo
    -0.68
    bd
    -0.67
    adv
    -0.66
    aden
    -0.66
    lain
    -0.66
    POSITIVE LOGITS
     congratulations
    0.89
     let
    0.88
     introdu
    0.87
     congr
    0.78
     apologize
    0.71
     Introduction
    0.70
     lets
    0.70
     apologies
    0.68
     FIX
    0.67
     suppose
    0.66
    Activations Density 0.080%

    No Known Activations