© 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. 9-RES-JB
    11. 2229
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies and individuals involved in business operations

    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
     trope
    -0.90
     coma
    -0.81
     characteristic
    -0.80
     intro
    -0.80
     reapp
    -0.79
     filibuster
    -0.79
     stump
    -0.79
     recess
    -0.78
     polarized
    -0.77
     sidel
    -0.75
    POSITIVE LOGITS
     Enterprises
    1.40
     Holdings
    1.40
     Industries
    1.31
     Ventures
    1.27
     Technologies
    1.21
     Corporation
    1.21
    Soft
    1.13
     Associates
    1.12
     Laboratories
    1.11
    isoft
    1.09
    Activations Density 0.666%

    No Known Activations