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. 0-RES-JB
    6. 3845
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in '-ably.'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe manner or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sect
    -0.60
     redistributed
    -0.57
     branch
    -0.56
     Orders
    -0.53
     follow
    -0.52
     mother
    -0.51
     followed
    -0.51
    NEW
    -0.50
     account
    -0.50
     sister
    -0.50
    POSITIVE LOGITS
    ably
    4.71
    able
    2.35
    ability
    2.13
    ibly
    1.97
    ables
    1.90
    ABLE
    1.89
    ingly
    1.76
    abl
    1.74
    abilities
    1.59
    atively
    1.57
    Activations Density 0.008%

    No Known Activations