© 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. 11-RES-JB
    11. 11597
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific words

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ispers
    -0.59
    ãĤ·
    -0.59
    ëĭ
    -0.56
    ographers
    -0.55
    ographer
    -0.54
     oblig
    -0.53
    ographies
    -0.53
    rehens
    -0.53
    reference
    -0.53
     eventually
    -0.52
    POSITIVE LOGITS
     behalf
    1.18
     steroids
    1.01
     Scrib
    1.00
     Tues
    0.99
     Thurs
    0.97
    eworld
    0.93
    etime
    0.92
     Sundays
    0.91
    yx
    0.91
     Fridays
    0.91
    Activations Density 0.134%

    No Known Activations