© 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. 11-RES-JB
    11. 2781
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or things yet to be determined

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating persistence or continuity of a state or situation

    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
    DragonMagazine
    -0.79
    gage
    -0.77
    ramid
    -0.69
    azeera
    -0.68
    dinand
    -0.67
    orsi
    -0.67
    iband
    -0.66
     TOUR
    -0.64
    isson
    -0.63
    ugh
    -0.63
    POSITIVE LOGITS
     unchanged
    1.33
     elusive
    1.21
     unsolved
    1.19
     intact
    1.19
     unresolved
    1.14
     untouched
    1.12
     unanswered
    1.08
     unclear
    1.03
     unsett
    1.00
     stubborn
    1.00
    Activations Density 0.054%

    No Known Activations