© 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. 9111
    Prev
    Next
    INDEX
    Explanations

    phrases indicating empowerment and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    first-person declarations of identity and empowerment

    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
    rities
    -0.67
    heny
    -0.63
    Disc
    -0.63
    pmwiki
    -0.62
    rarily
    -0.62
    ð
    -0.61
    asury
    -0.60
    rary
    -0.59
    inosaur
    -0.59
    arrell
    -0.59
    POSITIVE LOGITS
     hereby
    1.00
     presently
    0.96
     indeed
    0.96
     unable
    0.94
     NOT
    0.92
     currently
    0.92
     aware
    0.91
     not
    0.90
     indebted
    0.88
     surrounded
    0.87
    Activations Density 0.184%

    No Known Activations