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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 8984
    Prev
    Next
    INDEX
    Explanations

    financial institutions and related terms like JPMorgan Chase and partners

    oai_token-act-pair · gpt-3.5-turbo

    corporate entities and their partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    requ
    -0.79
    podcast
    -0.74
    liest
    -0.70
    tumblr
    -0.69
    kit
    -0.69
    alogue
    -0.69
    ĸļ
    -0.66
    nar
    -0.65
    anooga
    -0.65
    POSITIVE LOGITS
     Securities
    1.32
     Chase
    1.28
     Bank
    1.23
     Sachs
    1.22
     Holdings
    1.22
     Advis
    1.21
     Investors
    1.19
     Investments
    1.14
     LLP
    1.13
     Asset
    1.13
    Activations Density 0.138%

    No Known Activations