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. 19476
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "of" followed by an adjective and a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "something being" or "having" a characteristic or quality

    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
    RAW
    -0.84
    absolutely
    -0.79
    illions
    -0.74
    20439
    -0.73
    ALLY
    -0.73
    ULTS
    -0.72
     Truly
    -0.70
    loads
    -0.69
    iments
    -0.68
    ioxide
    -0.68
    POSITIVE LOGITS
     novelty
    1.02
     nuisance
    1.00
     tease
    0.99
     mystery
    0.97
     gamble
    0.95
     hassle
    0.94
     gimmick
    0.93
     deterrent
    0.93
     joke
    0.90
     stretch
    0.83
    Activations Density 0.092%

    No Known Activations