© 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. 16621
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "on"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "on" in various contexts

    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
    Applic
    -0.66
     presence
    -0.64
    Pokémon
    -0.64
    catentry
    -0.64
    Introduced
    -0.62
    Released
    -0.61
    Synopsis
    -0.61
    Card
    -0.61
     departing
    -0.60
     impending
    -0.59
    POSITIVE LOGITS
    Ô
    0.97
     unnoticed
    0.84
    levard
    0.73
    erk
    0.68
    vt
    0.67
    à¦
    0.66
    zag
    0.66
    govtrack
    0.65
    utical
    0.63
    interstitial
    0.63
    Activations Density 0.347%

    No Known Activations