© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3201
    Prev
    Next
    INDEX
    Explanations

    expressions related to reflective thoughts or musings

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or structures emphasizing a singular idea or viewpoint

    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
     boarding
    -0.67
     Laurent
    -0.65
     Antar
    -0.64
     retiring
    -0.64
     scattering
    -0.64
     Pony
    -0.63
     Yor
    -0.63
     rotating
    -0.63
     stumbling
    -0.62
     sleeping
    -0.62
    POSITIVE LOGITS
    should
    1.02
    uates
    1.00
    felt
    0.99
    s
    0.95
    imgur
    0.95
    Pg
    0.94
     beh
    0.93
    ï¸ı
    0.93
    cffffcc
    0.92
    sets
    0.91
    Activations Density 0.159%

    No Known Activations