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. 8-RES-JB
    6. 4523
    Prev
    Next
    INDEX
    Explanations

    companies and financial organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to financial institutions and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trope
    -0.86
     Racial
    -0.83
     poem
    -0.79
     mentally
    -0.78
     degener
    -0.78
     override
    -0.77
     schematic
    -0.77
     recess
    -0.77
     impe
    -0.77
     disorder
    -0.77
    POSITIVE LOGITS
    Shares
    1.40
     Holdings
    1.33
    Companies
    1.26
    Company
    1.23
    ibur
    1.11
     Corp
    1.09
    FX
    1.08
    Soft
    1.08
    cash
    1.07
    Pay
    1.05
    Activations Density 0.463%

    No Known Activations