© 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. 8-RES-JB
    11. 1192
    Prev
    Next
    INDEX
    Explanations

    words related to hydration and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to hydration and its importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.91
    éĹĺ
    -0.70
     Borough
    -0.69
     Keen
    -0.69
     Laugh
    -0.67
    istically
    -0.66
     Sands
    -0.66
    ãģ«
    -0.64
     Whale
    -0.64
     Mutual
    -0.64
    POSITIVE LOGITS
    rolog
    1.25
    ration
    1.23
    rox
    1.16
    rol
    1.10
    rogen
    1.08
    roph
    1.07
    rology
    1.06
    rop
    1.05
    rated
    1.04
    raph
    1.00
    Activations Density 0.028%

    No Known Activations