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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 2563
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial documents, specifically tax returns

    oai_token-act-pair · gpt-3.5-turbo

    references to tax returns

    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
    TAG
    -0.81
    å§«
    -0.77
    ãĥĦ
    -0.74
    zinski
    -0.71
    ker
    -0.69
    æĪ¦
    -0.66
    ETA
    -0.66
    γ
    -0.63
    ovie
    -0.63
    ¾
    -0.63
    POSITIVE LOGITS
     Transcript
    0.74
     filings
    0.73
     Rece
    0.72
     Taxes
    0.71
     payable
    0.69
     deposited
    0.69
    eed
    0.68
     uncovered
    0.68
     calculation
    0.67
     computation
    0.67
    Activations Density 0.037%

    No Known Activations