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. 7-RES-JB
    6. 18357
    Prev
    Next
    INDEX
    Explanations

    phrases related to flying over or above a location

    oai_token-act-pair · gpt-3.5-turbo

    instances of "flying" and related terms, particularly in contexts involving aircraft or aerial activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diaper
    -0.67
     hairc
    -0.66
    Introduced
    -0.65
    construct
    -0.64
    alysis
    -0.64
     chore
    -0.64
    ãĥĥãĥī
    -0.63
     recourse
    -0.63
    ophobia
    -0.63
     memor
    -0.62
    POSITIVE LOGITS
     Bermuda
    0.87
     Gibraltar
    0.86
     Jupiter
    0.85
    shore
    0.84
     Britain
    0.84
     northern
    0.82
     Earth
    0.81
     Antarctica
    0.81
     Guam
    0.80
     Canad
    0.80
    Activations Density 0.199%

    No Known Activations