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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2753
    Prev
    Next
    INDEX
    Explanations

    phrases with prepositions followed by descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "with" indicating a relationship or association

    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
    sburg
    -0.75
    matter
    -0.73
    henko
    -0.70
    TG
    -0.69
    press
    -0.68
    ertain
    -0.67
    Strike
    -0.67
    ovember
    -0.65
    Reuters
    -0.65
    olt
    -0.64
    POSITIVE LOGITS
    stood
    1.45
     lots
    1.12
     regard
    1.10
    drawn
    1.10
     plenty
    1.06
     regards
    1.04
     respect
    1.03
     minimal
    1.01
     fewer
    1.00
     ample
    0.99
    Activations Density 0.158%

    No Known Activations