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. 6-RES-JB
    6. 16009
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially streets or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to places or locations, especially involving the word "across" followed by another noun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.88
    uning
    -0.70
    trak
    -0.69
    hao
    -0.64
    Ut
    -0.64
    LY
    -0.60
     sparing
    -0.60
    fully
    -0.60
     chau
    -0.60
     nicknamed
    -0.60
    POSITIVE LOGITS
     rooft
    0.91
     aisle
    0.91
     country
    0.89
     globe
    0.84
     spectrum
    0.82
     boundaries
    0.81
    country
    0.80
     continent
    0.80
    Atlantic
    0.79
     rainbow
    0.79
    Activations Density 0.070%

    No Known Activations