© 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. 3-RES-JB
    11. 16540
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal development and improvement

    oai_token-act-pair · gpt-3.5-turbo

    elements related to personal growth and achieving a winning mindset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.70
     pdf
    -0.68
    âĢł
    -0.68
    1945
    -0.68
     purportedly
    -0.68
    vir
    -0.62
    Auth
    -0.61
     cens
    -0.60
     SHARES
    -0.60
    PDF
    -0.59
    POSITIVE LOGITS
     coaching
    1.01
     coached
    0.92
     coaches
    0.90
     teammates
    0.89
    Coach
    0.88
     scoreboard
    0.86
     adversity
    0.86
     Coach
    0.84
     undrafted
    0.83
     toughness
    0.80
    Activations Density 1.545%

    No Known Activations