© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    words related to excitement or enthusiasm

    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
     Sachs
    -0.66
    externalActionCode
    -0.64
     enriched
    -0.64
     horizontally
    -0.64
     Carlson
    -0.62
     industrial
    -0.61
     loose
    -0.59
     downhill
    -0.59
     horizontal
    -0.58
    lings
    -0.58
    POSITIVE LOGITS
    ursions
    1.50
    ursion
    1.49
    usable
    1.35
    ision
    1.24
    itement
    1.23
    retion
    1.21
    ulp
    1.19
    isions
    1.16
    utive
    1.12
    itable
    1.11
    Activations Density 0.021%

    No Known Activations