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

    Neuronpedia

    Jacobian LensNEW
    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. 4559
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers and modifiers indicating varying degrees or changes

    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
    umbn
    -0.84
    nos
    -0.69
     Loaded
    -0.63
    htaking
    -0.63
    çīĪ
    -0.63
    ommel
    -0.62
    pired
    -0.62
    £ı
    -0.62
    oi
    -0.62
    onomy
    -0.61
    POSITIVE LOGITS
     precip
    0.86
     lin
    0.79
     faster
    0.77
     exponentially
    0.76
     overnight
    0.76
     dramatically
    0.75
     sharply
    0.73
     rapidly
    0.72
     compared
    0.72
    versely
    0.71
    Activations Density 0.135%

    No Known Activations