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. 10-RES-JB
    6. 20075
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrasts between different subjects or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAST
    -0.77
    ESA
    -0.71
    ipers
    -0.68
    ART
    -0.67
    aukee
    -0.66
    weather
    -0.66
    BAT
    -0.65
    illion
    -0.64
    anie
    -0.63
    $$
    -0.63
    POSITIVE LOGITS
     contrast
    1.15
     particular
    0.91
     whom
    0.85
     nutshell
    0.81
     turn
    0.78
     conjunction
    0.74
     contrad
    0.71
    whose
    0.69
     cooperation
    0.69
     whose
    0.68
    Activations Density 0.071%

    No Known Activations