© 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. 9-RES-JB
    11. 4247
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'has'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interested
    -0.72
    uating
    -0.66
    bery
    -0.64
    lighting
    -0.62
     Pair
    -0.61
    Reading
    -0.61
    Give
    -0.59
    icking
    -0.59
    ipping
    -0.58
    âĻ¦
    -0.58
    POSITIVE LOGITS
     been
    1.52
     undergone
    1.34
     become
    1.31
    been
    1.24
     existed
    1.17
     traditionally
    1.16
     flourished
    1.14
     begun
    1.12
     risen
    1.12
     arisen
    1.10
    Activations Density 0.353%

    No Known Activations