© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 17051
    Prev
    Next
    INDEX
    Explanations

    references to whales

    oai_token-act-pair · gpt-3.5-turbo

    references to whales, specifically distinguishing between different types and contexts involving whales

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

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.87
    Interstitial
    -0.86
    senal
    -0.81
    uers
    -0.75
    yrinth
    -0.74
    ggles
    -0.68
    encing
    -0.67
    DM
    -0.64
    mble
    -0.64
    PT
    -0.64
    POSITIVE LOGITS
     whale
    1.33
     whales
    1.28
    odon
    1.06
     Whale
    1.02
     sharks
    1.01
     shark
    1.00
     dolphins
    0.96
    fish
    0.92
     carc
    0.91
     dolphin
    0.86
    Activations Density 0.015%

    No Known Activations