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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6391
    Prev
    Next
    INDEX
    Explanations

    numbers and monetary values mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and fundraising amounts

    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
     Goodell
    -0.68
     Scalia
    -0.67
    drivers
    -0.65
     Spicer
    -0.63
     Curry
    -0.63
     prescribe
    -0.63
     Burg
    -0.63
     counties
    -0.62
     fixme
    -0.59
     restraint
    -0.59
    POSITIVE LOGITS
     crowdfunding
    1.13
     fundraising
    1.04
     donations
    0.98
     fundra
    0.96
    funding
    0.95
     donation
    0.95
    fund
    0.94
    Fund
    0.93
    Reward
    0.92
     donated
    0.90
    Activations Density 0.146%

    No Known Activations