© 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. 306
    Prev
    Next
    INDEX
    Explanations

    phrases that express contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional scenarios or contrasts

    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
    themed
    -0.66
    senal
    -0.66
    arthed
    -0.66
     Booster
    -0.64
    umbn
    -0.64
    interstitial
    -0.62
     awaited
    -0.62
    nas
    -0.62
    Located
    -0.60
    ãĥij
    -0.59
    POSITIVE LOGITS
     therefore
    0.99
    cknowled
    0.97
    cknow
    0.95
    Therefore
    0.90
     moreover
    0.89
     contrast
    0.87
     analogy
    0.84
     exceptions
    0.84
     furthermore
    0.82
    nce
    0.82
    Activations Density 0.504%

    No Known Activations