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. 3-RES-JB
    6. 21494
    Prev
    Next
    INDEX
    Explanations

    references to tax-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENE
    -0.74
    sbm
    -0.70
    ilst
    -0.68
    lihood
    -0.68
    Ò
    -0.67
     Flavoring
    -0.67
     Ment
    -0.67
    hots
    -0.66
    Sensor
    -0.66
    uggest
    -0.66
    POSITIVE LOGITS
     liabilities
    0.90
     evasion
    0.90
     payable
    0.85
     levied
    0.85
     havens
    0.85
     dodging
    0.85
     liability
    0.85
     taxes
    0.83
     dodge
    0.82
     taxation
    0.78
    Activations Density 0.038%

    No Known Activations