© 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. 15141
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases contrasting with societal expectations or norms

    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
    velt
    -0.72
    stru
    -0.69
    age
    -0.68
    ixel
    -0.67
    pires
    -0.65
    FAQ
    -0.64
    eur
    -0.62
    aspers
    -0.62
    Age
    -0.61
    POSITIVE LOGITS
     necessarily
    1.50
     bothering
    1.00
    epad
    0.95
    withstanding
    0.95
    icably
    0.93
    eworthy
    0.88
     unlike
    0.84
     merely
    0.82
    ifying
    0.80
    ific
    0.78
    Activations Density 0.068%

    No Known Activations