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. 5-RES-JB
    6. 3300
    Prev
    Next
    INDEX
    Explanations

    mentions of taxes, fees, and financial levies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxation and levies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥ¬
    -0.74
    ¥µ
    -0.73
     Shooter
    -0.71
    swing
    -0.70
     ABE
    -0.69
     Patriarch
    -0.67
    utherland
    -0.67
    feed
    -0.66
    ciating
    -0.66
    д
    -0.65
    POSITIVE LOGITS
     lev
    0.87
    ried
    0.84
     levied
    0.78
     levy
    0.73
     withd
    0.73
    riage
    0.73
    pless
    0.72
    worms
    0.71
    enance
    0.70
    itated
    0.70
    Activations Density 0.039%

    No Known Activations