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. 8-RES-JB
    6. 2825
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investments involving large sums of money

    oai_token-act-pair · gpt-3.5-turbo

    references to multi-billion dollar investments or projects

    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
     Kamp
    -0.75
     AVG
    -0.74
     Cecil
    -0.74
     Finch
    -0.72
     Klaus
    -0.72
     Roe
    -0.71
     Rutherford
    -0.70
     Polk
    -0.69
     Herrera
    -0.69
     Byrd
    -0.68
    POSITIVE LOGITS
    dimensional
    1.41
    functional
    1.24
    disciplinary
    1.20
    ethnic
    1.20
    national
    1.11
    purpose
    1.11
    agency
    1.10
    colored
    1.10
    million
    1.08
    interstitial
    1.08
    Activations Density 0.023%

    No Known Activations