© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    text related to the word "naturally" occurring habitually or typically in a situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "naturally."

    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
     Millennium
    -0.76
     Straw
    -0.74
    pled
    -0.72
     Blades
    -0.69
    andals
    -0.69
    ultz
    -0.68
    raints
    -0.68
    seless
    -0.68
     Telescope
    -0.67
     Horizons
    -0.66
    POSITIVE LOGITS
     occurring
    0.99
     attracted
    0.88
     combust
    0.82
     regenerate
    0.82
    uced
    0.81
     dissip
    0.80
     inclined
    0.78
     arises
    0.78
    gyn
    0.77
     regener
    0.77
    Activations Density 0.017%

    No Known Activations