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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2-RES-JB
    6. 22594
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in 'ous' with a strong emphasis on the word "grievous"

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe something as large, extreme, or overwhelming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rette
    -0.74
    ellen
    -0.74
    é¾įå
    -0.72
    ARC
    -0.72
    aminer
    -0.71
    ublic
    -0.71
    âĸ¬âĸ¬
    -0.69
    ilogy
    -0.69
    ERA
    -0.69
    udeb
    -0.67
    POSITIVE LOGITS
    ous
    1.17
    Magikarp
    1.16
    ness
    0.99
    ity
    0.93
     amounts
    0.93
    nesses
    0.83
    ly
    0.81
    ities
    0.81
    soever
    0.80
    lihood
    0.78
    Activations Density 0.012%

    No Known Activations