© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 18841
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "in"

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating location or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tle
    -0.77
    facts
    -0.75
    bats
    -0.73
    ucket
    -0.69
    spection
    -0.68
     pony
    -0.67
    chery
    -0.67
    rone
    -0.64
    Cow
    -0.63
    cher
    -0.63
    POSITIVE LOGITS
     Seymour
    0.68
     Ital
    0.66
     indo
    0.65
     Siber
    0.64
     Rasm
    0.64
     Hudson
    0.63
     fert
    0.63
     trop
    0.62
    asso
    0.62
     Wass
    0.61
    Activations Density 0.000%

    No Known Activations