© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 12923
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts, particularly the chest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "chest."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.84
     Democr
    -0.76
     Vide
    -0.73
     CSI
    -0.71
     Users
    -0.68
     Flickr
    -0.66
    VICE
    -0.64
    EEE
    -0.64
    ROR
    -0.63
     newsp
    -0.63
    POSITIVE LOGITS
    nuts
    1.18
    nut
    1.09
     chest
    1.00
    erton
    0.95
    piece
    0.89
     cavity
    0.87
    plate
    0.87
     chests
    0.87
    ilage
    0.81
    lain
    0.77
    Activations Density 0.005%

    No Known Activations