© 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. 11-RES-JB
    11. 20683
    Prev
    Next
    INDEX
    Explanations

    terms related to customization options and settings in devices or software

    oai_token-act-pair · gpt-3.5-turbo

    terms related to customization and personalization of objects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.74
     Sidney
    -0.73
    evidence
    -0.72
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.70
    ItemTracker
    -0.69
     underest
    -0.66
    interstitial
    -0.65
     hypoc
    -0.64
    heed
    -0.64
     Disclosure
    -0.63
    POSITIVE LOGITS
     customization
    1.65
     customizable
    1.58
     customize
    1.51
     presets
    1.36
     configurations
    1.28
     customized
    1.26
     options
    1.22
     choices
    1.22
     config
    1.19
     Custom
    1.18
    Activations Density 0.501%

    No Known Activations