Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16216
    Prev
    Next
    INDEX
    Explanations

    phrases related to taxes and financial regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to income and taxation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sensor
    -0.72
    insk
    -0.72
    zai
    -0.71
     Jace
    -0.65
    ĸļ
    -0.64
    natureconservancy
    -0.63
     Polic
    -0.63
    Dialogue
    -0.63
    metry
    -0.62
    ji
    -0.62
    POSITIVE LOGITS
     taxable
    1.65
     taxed
    1.47
     deductions
    1.42
     dividends
    1.36
     deductible
    1.33
     deduction
    1.25
     income
    1.22
     dividend
    1.15
     estates
    1.14
     deduct
    1.13
    Activations Density 0.346%

    No Known Activations