© 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. 0-RES-JB
    11. 11917
    Prev
    Next
    INDEX
    Explanations

    intensifiers related to the stomach area

    oai_token-act-pair · gpt-3.5-turbo

    terms related to body anatomy, specifically the abdomen and womb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dates
    -0.69
    hoff
    -0.69
    CD
    -0.67
     Alph
    -0.64
    mith
    -0.64
    Documents
    -0.64
    ange
    -0.63
    TAIN
    -0.63
     Jefferson
    -0.62
     Flavoring
    -0.62
    POSITIVE LOGITS
     belly
    3.59
     abdomen
    1.39
     womb
    1.33
     waist
    1.01
     tum
    0.99
     abdominal
    0.98
     uterus
    0.93
     shoulder
    0.90
     bos
    0.89
     pelvic
    0.87
    Activations Density 0.033%

    No Known Activations