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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 21821
    Prev
    Next
    INDEX
    Explanations

    information related to sports events, fighters, and matches, particularly in the context of mixed martial arts

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings or statistics associated with sports events and fighters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hashtag
    -0.68
    nesday
    -0.66
     leaked
    -0.64
     flare
    -0.61
     ripple
    -0.59
     debit
    -0.59
     allot
    -0.59
     lun
    -0.58
     aeros
    -0.57
     bulletin
    -0.57
    POSITIVE LOGITS
    76561
    0.93
    Weight
    0.75
    Īè
    0.72
    ometown
    0.72
    married
    0.71
    =~=~
    0.71
    ģĸ
    0.69
    çͰ
    0.68
    é¾
    0.66
    é¾įå¥ij士
    0.65
    Activations Density 0.139%

    No Known Activations