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

    Neuronpedia

    APICircuit 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. 18805
    Prev
    Next
    INDEX
    Explanations

    financial terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to financial topics or discussions

    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
    lain
    -0.81
    gger
    -0.75
     Weber
    -0.75
     Nieto
    -0.74
    poke
    -0.70
     Tune
    -0.69
    lr
    -0.69
     Zin
    -0.67
     Reborn
    -0.67
    IRO
    -0.66
    POSITIVE LOGITS
     literacy
    0.89
     transactions
    0.89
     advisor
    0.89
     advisors
    0.88
    assets
    0.88
     institutions
    0.86
     adviser
    0.86
     advisers
    0.86
     disclosures
    0.84
     institution
    0.82
    Activations Density 0.021%

    No Known Activations