© 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. 2973
    Prev
    Next
    INDEX
    Explanations

    instances where the word "though" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "though" to indicate contrasting ideas or conditions

    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
    anwhile
    -0.70
    ufact
    -0.66
     Cosponsors
    -0.65
    ragon
    -0.64
    istance
    -0.63
    adesh
    -0.62
     Learns
    -0.60
    tnc
    -0.59
    urated
    -0.59
    actly
    -0.58
    POSITIVE LOGITS
     admittedly
    1.05
    ts
    0.85
     thankfully
    0.85
     fortunately
    0.76
    ,
    0.75
    tons
    0.74
    ,...
    0.74
     technically
    0.72
     sadly
    0.70
    ,,
    0.70
    Activations Density 0.043%

    No Known Activations