© 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. 10-RES-JB
    11. 8564
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "by" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "by" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.75
    SPONSORED
    -0.73
    hement
    -0.69
    istant
    -0.69
    itled
    -0.65
    llor
    -0.65
    TB
    -0.64
    rah
    -0.63
    cia
    -0.62
    asive
    -0.61
    POSITIVE LOGITS
     virtue
    1.24
     mistake
    1.19
     accident
    1.07
     chance
    1.05
     coincidence
    0.98
    catch
    0.95
     parachute
    0.95
     candle
    0.94
    products
    0.90
     leaps
    0.89
    Activations Density 0.103%

    No Known Activations