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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13855
    Prev
    Next
    INDEX
    Explanations

    phrases related to toughness or strength

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ough" and its related morphological forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Copenhagen
    -0.69
     Lisbon
    -0.67
    piece
    -0.65
     Lutheran
    -0.64
     Wand
    -0.61
     Triumph
    -0.61
     Borough
    -0.61
     Carlson
    -0.60
    crew
    -0.60
     Emin
    -0.60
    POSITIVE LOGITS
    oug
    1.29
    hest
    1.09
    avored
    0.96
    heed
    0.88
    omen
    0.87
    lean
    0.84
    itives
    0.83
    cipl
    0.81
    ener
    0.81
    isoft
    0.80
    Activations Density 0.028%

    No Known Activations