© 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. 18197
    Prev
    Next
    INDEX
    Explanations

    mentions of tax-related terms and numbers

    oai_token-act-pair · gpt-3.5-turbo

    topics related to taxation and income levels

    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
    DragonMagazine
    -0.82
    Sensor
    -0.81
     Riot
    -0.77
    Dialogue
    -0.77
    Mos
    -0.75
    Scene
    -0.74
     Hirosh
    -0.74
    CVE
    -0.72
     Milo
    -0.72
    mos
    -0.72
    POSITIVE LOGITS
     taxable
    1.64
     taxed
    1.50
     deductible
    1.43
     tax
    1.41
     income
    1.37
     taxes
    1.36
     deductions
    1.30
     taxation
    1.25
     deduct
    1.24
     Tax
    1.23
    Activations Density 0.595%

    No Known Activations