© 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. 4-RES-JB
    11. 7380
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "though."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or hypothetical situations

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

    No Comments

    Negative Logits
    Winged
    -0.66
     AZ
    -0.63
     Bless
    -0.63
     Horses
    -0.62
    vant
    -0.62
    backer
    -0.62
    Offline
    -0.61
     Highlights
    -0.61
    Bas
    -0.61
    03
    -0.61
    POSITIVE LOGITS
    acho
    0.69
    ovie
    0.68
     "$:/
    0.67
     causation
    0.66
    AMI
    0.65
    lihood
    0.64
    oche
    0.64
    icago
    0.62
    antha
    0.62
    tha
    0.61
    Activations Density 0.006%

    No Known Activations