© 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. 9-RES-JB
    11. 4235
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thought" followed by a positive evaluation or thoughtful consideration

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.81
     Nanto
    -0.74
    ãĤ¬
    -0.74
    è¦ļéĨĴ
    -0.73
    ãĤº
    -0.72
    OURCE
    -0.72
    adra
    -0.68
    anwhile
    -0.64
     guiName
    -0.63
    */(
    -0.62
    POSITIVE LOGITS
     joking
    0.97
     cute
    0.93
     funny
    0.88
     invincible
    0.84
     hilarious
    0.82
     kidding
    0.82
     quaint
    0.80
     cool
    0.79
     silly
    0.75
     innocuous
    0.75
    Activations Density 0.183%

    No Known Activations