© 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. 8-RES-JB
    11. 6304
    Prev
    Next
    INDEX
    Explanations

    mentions of technology startups and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to startups and their innovative solutions

    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
     recess
    -0.80
    asion
    -0.71
     Reagan
    -0.70
     Protestant
    -0.69
    ewitness
    -0.68
    veyard
    -0.67
    abilia
    -0.67
    enged
    -0.67
    ghazi
    -0.66
     funer
    -0.66
    POSITIVE LOGITS
     crowdfunding
    1.09
    laun
    0.94
    Laun
    0.94
     innovative
    0.91
     aims
    0.89
    plugins
    0.89
     partnering
    0.89
     Kickstarter
    0.88
    mable
    0.88
     creators
    0.87
    Activations Density 0.717%

    No Known Activations