© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23487
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and information, potentially related to mobile devices or software

    oai_token-act-pair · gpt-3.5-turbo

    instances of structured descriptions of creatures or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrang
    -0.67
     destro
    -0.66
    sit
    -0.65
     agre
    -0.63
    akespe
    -0.63
    omever
    -0.61
     predec
    -0.61
     undermin
    -0.60
     Vaugh
    -0.60
    hovah
    -0.59
    POSITIVE LOGITS
     Profile
    1.01
     Overview
    0.84
     Brewing
    0.82
    ®
    0.79
    ¶
    0.77
     Calculator
    0.77
     Redux
    0.77
     Releases
    0.75
     âĵĺ
    0.75
     Basics
    0.74
    Activations Density 0.713%

    No Known Activations