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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 11793
    Prev
    Next
    INDEX
    Explanations

    words related to sports titles

    oai_token-act-pair · gpt-3.5-turbo

    references to titles in competitive contexts

    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
     Spicer
    -0.68
    oidal
    -0.68
    pmwiki
    -0.65
     Gork
    -0.65
     Spice
    -0.63
    esthetic
    -0.62
    velength
    -0.62
    ajor
    -0.62
    iasco
    -0.61
     Lindsey
    -0.61
    POSITIVE LOGITS
    holder
    0.91
    manship
    0.88
     contender
    0.88
    marks
    0.85
    title
    0.85
     titles
    0.83
    holders
    0.83
     title
    0.83
    ifications
    0.80
     holder
    0.79
    Activations Density 0.016%

    No Known Activations