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. 2-RES-JB
    6. 20518
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in 'fully'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "fully."

    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
     Greenwich
    -0.68
    senal
    -0.63
    ERA
    -0.61
    afety
    -0.60
     Keys
    -0.60
     Rapp
    -0.60
    itu
    -0.59
     Mehran
    -0.58
    olan
    -0.58
     Revenue
    -0.58
    POSITIVE LOGITS
    wash
    0.85
    ctuary
    0.80
    nerg
    0.76
    hyd
    0.76
    theless
    0.73
     discharged
    0.72
     satisfied
    0.72
    borg
    0.68
    ness
    0.68
     fulfilled
    0.68
    Activations Density 0.007%

    No Known Activations