© 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. 3-RES-JB
    11. 6130
    Prev
    Next
    INDEX
    Explanations

    terms related to customization and personalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to customization and modifying something to fit personal preferences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.86
    REL
    -0.73
    rough
    -0.72
    Torrent
    -0.72
    Jordan
    -0.71
    á
    -0.70
    upon
    -0.69
    BILITIES
    -0.69
    wick
    -0.68
    802
    -0.68
    POSITIVE LOGITS
     customization
    1.27
    isable
    1.11
     customized
    0.93
     customize
    0.89
     settings
    0.88
     tailored
    0.87
     customizable
    0.87
    izable
    0.84
     tailor
    0.83
     decoration
    0.80
    Activations Density 0.016%

    No Known Activations