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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20797
    Prev
    Next
    INDEX
    Explanations

    financial terms related to fundraising or project funding

    oai_token-act-pair · gpt-3.5-turbo

    references to crowdfunding and financial goals

    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
    gregation
    -0.72
    ictionary
    -0.71
    heter
    -0.71
    ESE
    -0.71
    ophen
    -0.71
    Trend
    -0.69
    unction
    -0.69
    alter
    -0.69
    Column
    -0.67
    enh
    -0.67
    POSITIVE LOGITS
     crowdfunding
    1.85
     Kickstarter
    1.68
     backers
    1.35
     funding
    1.30
     fundraising
    1.27
     financing
    1.20
     investors
    1.19
     prototypes
    1.17
     Funding
    1.17
     founders
    1.16
    Activations Density 0.877%

    No Known Activations