© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating gradual progress or incremental steps forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ghazi
    -0.67
    igslist
    -0.61
    htaking
    -0.58
    urated
    -0.57
    onduct
    -0.57
    unci
    -0.56
    ictions
    -0.56
    idth
    -0.55
    zeb
    -0.55
    cius
    -0.55
    POSITIVE LOGITS
     closer
    1.36
     worse
    1.28
     richer
    1.28
     better
    1.24
     cheaper
    1.24
     farther
    1.23
     louder
    1.22
     faster
    1.21
     higher
    1.20
     safer
    1.20
    Activations Density 0.497%

    No Known Activations