© 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. 7-RES-JB
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    phrases related to expenses or expenditures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ball
    -0.81
    footed
    -0.73
    kus
    -0.71
    âĸ¬âĸ¬
    -0.68
    milo
    -0.68
    balls
    -0.66
    picking
    -0.66
    warts
    -0.64
    ters
    -0.64
     litter
    -0.63
    POSITIVE LOGITS
    onential
    1.48
    ansion
    1.36
    anded
    1.35
    onent
    1.32
    osed
    1.30
    ression
    1.23
    ulsion
    1.18
    anding
    1.17
    ressive
    1.15
    edia
    1.08
    Activations Density 0.031%

    No Known Activations