© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 4493
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing interest or curiosity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.83
    RIP
    -0.81
    SON
    -0.78
    Fail
    -0.74
    City
    -0.70
    IRE
    -0.70
    aurus
    -0.70
    aucus
    -0.70
    lag
    -0.70
    GE
    -0.69
    POSITIVE LOGITS
     preserving
    1.45
     seeing
    1.39
     acquiring
    1.39
     pursuing
    1.39
     exploring
    1.36
     helping
    1.33
     learning
    1.28
     obtaining
    1.27
     joining
    1.27
     finding
    1.26
    Activations Density 0.104%

    No Known Activations