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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19485
    Prev
    Next
    INDEX
    Explanations

    references to notable figures such as leaders, icons, whistleblowers, and nominees, particularly in a political context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political positions and figures

    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
    MpServer
    -0.79
    erial
    -0.75
    isoft
    -0.73
    ignant
    -0.71
    wcsstore
    -0.71
    ciplinary
    -0.70
    ename
    -0.68
    liga
    -0.67
    */(
    -0.67
    lez
    -0.66
    POSITIVE LOGITS
     Stephen
    1.06
     Bruce
    1.03
     Tony
    1.03
     Steve
    1.03
     Gina
    1.02
     Otto
    1.02
     Julius
    1.01
     Karl
    1.00
     Larry
    1.00
     Robert
    0.99
    Activations Density 0.290%

    No Known Activations