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. 8-RES-JB
    6. 20999
    Prev
    Next
    INDEX
    Explanations

    locations near a border

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anew
    -0.81
    fully
    -0.77
    rix
    -0.71
    manship
    -0.70
     distinguishes
    -0.68
    ãĥ»
    -0.68
     wisely
    -0.67
     indeed
    -0.65
    ful
    -0.64
    vier
    -0.64
    POSITIVE LOGITS
     entrance
    1.13
     horizon
    1.06
     nearest
    1.04
     intersection
    0.99
     periphery
    0.95
     end
    0.94
     entrances
    0.92
     shores
    0.90
     borders
    0.89
     center
    0.89
    Activations Density 0.171%

    No Known Activations