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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 3883
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial matters and taxes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of taxes and related financial topics

    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
    rame
    -0.81
    haus
    -0.70
    board
    -0.69
    picture
    -0.66
    ouse
    -0.66
     Kali
    -0.65
    break
    -0.65
    ature
    -0.64
    mb
    -0.64
    isk
    -0.62
    POSITIVE LOGITS
     taxes
    3.77
     Taxes
    3.19
     taxation
    2.52
     tax
    2.32
    tax
    2.19
    Tax
    2.11
     Tax
    1.95
     taxed
    1.86
     taxing
    1.82
     tariffs
    1.77
    Activations Density 0.017%

    No Known Activations