© 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. 0-RES-JB
    11. 15187
    Prev
    Next
    INDEX
    Explanations

    numerical measurements in units of distance

    oai_token-act-pair · gpt-3.5-turbo

    references to distances measured in miles or kilometers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emer
    -0.65
    Art
    -0.64
    ham
    -0.64
     Rosenberg
    -0.63
     Caps
    -0.61
    erg
    -0.61
    ahl
    -0.61
    ive
    -0.60
     prim
    -0.60
    andro
    -0.59
    POSITIVE LOGITS
     mile
    3.81
    mile
    2.63
     miles
    2.28
     kilomet
    2.27
     Mile
    2.01
     kilometres
    1.51
     kilometers
    1.51
     km
    1.37
    km
    1.35
     mileage
    1.33
    Activations Density 0.013%

    No Known Activations