© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17838
    Prev
    Next
    INDEX
    Explanations

    instances related to tax

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osw
    -0.76
    hots
    -0.73
    lihood
    -0.71
     Hast
    -0.70
     Jenner
    -0.70
     Despair
    -0.68
    tsky
    -0.67
     Yug
    -0.66
    emonic
    -0.64
    itar
    -0.63
    POSITIVE LOGITS
     liabilities
    1.10
     payable
    1.07
    payer
    1.06
     levied
    1.05
    paying
    0.97
     liability
    0.96
     collectors
    0.94
    payers
    0.94
     receipts
    0.92
     owed
    0.90
    Activations Density 0.054%

    No Known Activations