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. 9-RES-JB
    6. 21674
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons between urban areas

    oai_token-act-pair · gpt-3.5-turbo

    descriptions and comparisons of urban areas or cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scept
    -0.81
     torture
    -0.79
     Hermes
    -0.76
     authorised
    -0.76
     armour
    -0.74
    secret
    -0.72
     analys
    -0.71
    witch
    -0.70
     Spectre
    -0.70
    ãĥĹ
    -0.69
    POSITIVE LOGITS
     suburbs
    1.46
     metropolitan
    1.41
     cities
    1.36
     urban
    1.36
     neighborhoods
    1.34
     towns
    1.32
     geographically
    1.30
     Cities
    1.29
     statewide
    1.29
    Urban
    1.26
    Activations Density 1.059%

    No Known Activations