© 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. 3-RES-JB
    6. 5972
    Prev
    Next
    INDEX
    Explanations

    physical body parts, specifically the chest area

    oai_token-act-pair · gpt-3.5-turbo

    references to the chest area, particularly in contexts related to health or injury

    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
     GOODMAN
    -0.90
     CSI
    -0.75
    VICE
    -0.73
    actionDate
    -0.73
     newsp
    -0.72
    DEM
    -0.71
     Democr
    -0.70
     Users
    -0.68
    FB
    -0.68
     Trend
    -0.68
    POSITIVE LOGITS
    nuts
    1.30
    nut
    1.17
     cavity
    1.07
    erton
    0.98
     chest
    0.95
    plate
    0.95
    piece
    0.92
     freezer
    0.87
     chests
    0.84
    uit
    0.83
    Activations Density 0.006%

    No Known Activations