© 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. 15416
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "EN" at high activation levels, potentially related to technology products or other entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "EN" or related concepts, likely indicating a product line or brand associated with technology

    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
     nearby
    -0.62
     Pac
    -0.61
     Pax
    -0.61
     pole
    -0.60
    itiz
    -0.59
     scoop
    -0.59
     Hood
    -0.59
     sparse
    -0.59
     Cal
    -0.58
     churn
    -0.57
    POSITIVE LOGITS
    EN
    3.98
    ENS
    2.34
    ENE
    1.89
    en
    1.72
    END
    1.72
    ENG
    1.71
    ENA
    1.69
    ens
    1.63
    ener
    1.60
    ENC
    1.59
    Activations Density 0.008%

    No Known Activations