© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 4817
    Prev
    Next
    INDEX
    Explanations

    mentions of funding rounds and venture capital investments

    oai_token-act-pair · gpt-3.5-turbo

    financial terms related to startup funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eisenhower
    -0.80
    bestos
    -0.79
    atche
    -0.78
     "$:/
    -0.78
     Chamberlain
    -0.78
    humane
    -0.76
    aukee
    -0.76
    armor
    -0.75
    acists
    -0.75
    helm
    -0.74
    POSITIVE LOGITS
     ICO
    1.63
     IPO
    1.59
     VC
    1.56
     startups
    1.53
     Venture
    1.50
     crowdfunding
    1.47
     Ventures
    1.44
     investors
    1.43
     Founders
    1.37
     founders
    1.37
    Activations Density 0.566%

    No Known Activations