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. 1-RES-JB
    6. 11985
    Prev
    Next
    INDEX
    Explanations

    titles and names containing the word "roy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Roy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.69
     Ammo
    -0.65
    iquid
    -0.64
     Hurricanes
    -0.60
     Ident
    -0.60
     realistic
    -0.60
     Disorder
    -0.59
    INESS
    -0.59
     Trave
    -0.59
     range
    -0.59
    POSITIVE LOGITS
    roy
    1.14
    alties
    1.05
    doms
    0.92
    rence
    0.89
    imet
    0.87
    alty
    0.87
    don
    0.85
    alist
    0.83
    rey
    0.81
    din
    0.80
    Activations Density 0.007%

    No Known Activations