© 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. 3-RES-JB
    11. 3007
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in a" and similar constructions

    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
     grasp
    -0.73
    peat
    -0.67
     substrate
    -0.67
     confines
    -0.65
     cess
    -0.63
    allery
    -0.63
    oler
    -0.62
    case
    -0.62
     plantation
    -0.60
    enment
    -0.59
    POSITIVE LOGITS
     sarcast
    0.77
     Cly
    0.68
    Quotes
    0.68
    Bloomberg
    0.65
     "#
    0.63
    èĪ
    0.63
    Pie
    0.62
    CTV
    0.61
    å£
    0.60
    çīĪ
    0.59
    Activations Density 0.817%

    No Known Activations