© 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. 7-RES-JB
    11. 1657
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or regularity

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regate
    -0.77
    ipeg
    -0.74
    doms
    -0.73
    ortmund
    -0.73
     scares
    -0.71
    idences
    -0.70
    might
    -0.69
     Increases
    -0.66
    would
    -0.65
    izes
    -0.65
    POSITIVE LOGITS
     supposed
    1.05
     considered
    0.99
     going
    0.99
     synonymous
    0.93
     able
    0.90
     capable
    0.90
     regarded
    0.89
     accessible
    0.86
     gonna
    0.86
    omorphic
    0.85
    Activations Density 0.331%

    No Known Activations