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. 0-RES-JB
    6. 10860
    Prev
    Next
    INDEX
    Explanations

    mentions of financial investments and terms related to finance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial or economic investments

    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
     Blaz
    -0.76
     Claud
    -0.75
    £ı
    -0.74
    ï¸
    -0.70
     Nero
    -0.69
    hid
    -0.68
    bra
    -0.67
    rid
    -0.63
    vous
    -0.63
     Bates
    -0.63
    POSITIVE LOGITS
     investment
    3.49
     investments
    2.62
     Investment
    2.52
     investing
    2.09
     investor
    1.92
     invest
    1.92
    invest
    1.84
     investors
    1.78
     invested
    1.76
     Investments
    1.74
    Activations Density 0.014%

    No Known Activations