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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 18630
    Prev
    Next
    INDEX
    Explanations

    words related to taxes, such as "tax", "deductions", "income", "law", "returns", and "liability"

    oai_token-act-pair · gpt-3.5-turbo

    topics related to taxes and financial aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynthesis
    -0.75
    lain
    -0.74
    urat
    -0.70
     Bundy
    -0.70
    Minecraft
    -0.65
    rupulous
    -0.65
    ora
    -0.65
    aeda
    -0.64
    ////////////////
    -0.63
    hap
    -0.61
    POSITIVE LOGITS
     accessories
    0.81
     parap
    0.81
     specialists
    0.74
     modules
    0.73
     terminology
    0.72
     advisory
    0.70
     lumin
    0.70
     jargon
    0.69
     identifiers
    0.69
     literacy
    0.68
    Activations Density 0.594%

    No Known Activations