© 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. 3-RES-JB
    11. 4994
    Prev
    Next
    INDEX
    Explanations

    the word "clear" used in a declarative or explanatory context

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing clarity or transparency in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Loft
    -0.72
     Rou
    -0.72
    erves
    -0.65
    ufact
    -0.64
    anged
    -0.62
     Bowling
    -0.62
    iddling
    -0.60
    heng
    -0.60
    unte
    -0.59
    oleon
    -0.59
    POSITIVE LOGITS
    ances
    0.97
     clear
    0.89
    iary
    0.79
     clears
    0.76
     sailing
    0.75
    ãĤ¦
    0.74
    tale
    0.73
    ãĤ¼
    0.72
    ãĥķãĤ©
    0.71
     distinction
    0.71
    Activations Density 0.013%

    No Known Activations