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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 5530
    Prev
    Next
    INDEX
    Explanations

    terms related to taxes or financial income

    oai_token-act-pair · gpt-3.5-turbo

    references to taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lead
    -0.66
     Gamma
    -0.64
     Resp
    -0.63
     settings
    -0.63
     lead
    -0.62
     Out
    -0.61
     peers
    -0.61
     Inst
    -0.60
     threads
    -0.60
     highlights
    -0.60
    POSITIVE LOGITS
    tax
    3.95
    Tax
    2.18
     Taxes
    1.44
     taxes
    1.28
     tax
    1.28
     taxed
    1.24
     taxation
    1.23
    license
    1.08
    cash
    1.04
    budget
    1.03
    Activations Density 0.014%

    No Known Activations