© 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. 6-RES-JB
    11. 9257
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "figured" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I figured" indicating personal realizations or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idium
    -0.72
    pes
    -0.72
    Real
    -0.69
    vette
    -0.67
    ewitness
    -0.65
    apes
    -0.65
    reports
    -0.65
    kw
    -0.65
     Machina
    -0.63
    perty
    -0.63
    POSITIVE LOGITS
    sonian
    0.92
     prominently
    0.83
    istically
    0.80
     Rasmussen
    0.67
     Ducks
    0.65
     underdog
    0.63
     strategically
    0.63
    utory
    0.62
    inery
    0.62
     Haram
    0.61
    Activations Density 0.026%

    No Known Activations