© 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. 12-RES-JB
    11. 4307
    Prev
    Next
    INDEX
    Explanations

    the letter 'g' followed by a number indicating the strength of the match

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words that start with the letter "g"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gearing
    -0.66
     Bree
    -0.66
     Down
    -0.64
     Chains
    -0.63
     Nieto
    -0.62
     Eleven
    -0.61
     Ples
    -0.61
     AMERICA
    -0.61
     exception
    -0.61
     Borders
    -0.60
    POSITIVE LOGITS
    raphics
    1.53
    ospel
    1.50
    arden
    1.41
    ifts
    1.38
    athering
    1.37
    raphic
    1.37
    ift
    1.31
    iant
    1.30
    orge
    1.29
    hetto
    1.28
    Activations Density 0.018%

    No Known Activations