© 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. 12-RES-JB
    11. 2703
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by the word "the"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "the" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     kindly
    -0.66
     appreci
    -0.65
     congrat
    -0.62
     Sus
    -0.61
     cumbers
    -0.60
     Il
    -0.59
     Wond
    -0.57
     inoc
    -0.57
     laud
    -0.57
     invalid
    -0.56
    POSITIVE LOGITS
    atre
    1.32
    ater
    1.15
    ATER
    1.10
    ory
    1.08
    ORY
    0.98
    arted
    0.97
    mes
    0.97
    aters
    0.92
    oret
    0.90
    DragonMagazine
    0.88
    Activations Density 0.031%

    No Known Activations