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. 10-RES-JB
    6. 23774
    Prev
    Next
    INDEX
    Explanations

    the word "Six"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Six" and related numerical themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.70
     depression
    -0.70
     redist
    -0.68
    webkit
    -0.67
     textbook
    -0.65
     slowdown
    -0.64
     DOI
    -0.63
    activity
    -0.61
     confirmation
    -0.61
    auder
    -0.61
    POSITIVE LOGITS
     Hundred
    1.17
     Feet
    1.17
     Mile
    1.12
     Peaks
    1.05
     Oaks
    1.04
     Eyes
    1.04
     Thousand
    1.02
     Faces
    0.98
     Dollar
    0.96
     Roses
    0.96
    Activations Density 0.051%

    No Known Activations