© 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. 10-RES-JB
    11. 3192
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of taxes

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.86
    oyal
    -0.83
    istar
    -0.83
    é¾įåĸļ士
    -0.81
    itness
    -0.78
    ÃįÃį
    -0.72
    ij士
    -0.67
    arya
    -0.66
    Ô
    -0.66
    meet
    -0.66
    POSITIVE LOGITS
     hike
    1.33
     repeal
    1.24
     exemption
    1.14
     proposal
    1.11
     moratorium
    1.07
     exemptions
    1.05
     loophole
    1.04
     repealed
    1.01
     imposed
    0.97
     levied
    0.97
    Activations Density 0.133%

    No Known Activations