© 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. 17142
    Prev
    Next
    INDEX
    Explanations

    terms related to business, ethics, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    key social issues and structural inequalities

    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
    noon
    -0.66
    eday
    -0.65
    arnaev
    -0.64
     Canaver
    -0.64
    Pod
    -0.61
    artisan
    -0.60
     similarly
    -0.60
     Definitive
    -0.60
     Klu
    -0.60
    ledged
    -0.60
    POSITIVE LOGITS
     etc
    1.10
    fulness
    0.72
    ,
    0.70
     shortages
    0.69
     responsiveness
    0.69
    ,...
    0.68
    worthiness
    0.66
     agendas
    0.65
    lessness
    0.64
    smanship
    0.64
    Activations Density 0.250%

    No Known Activations