© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 15024
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city of Newcastle

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Newcastle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viol
    -0.95
     violate
    -0.76
    CP
    -0.72
     violated
    -0.72
     flavors
    -0.71
     categorized
    -0.71
     intentionally
    -0.68
    II
    -0.67
     color
    -0.66
     ++
    -0.66
    POSITIVE LOGITS
     Newcastle
    3.61
    castle
    2.02
     Sunderland
    1.90
     Leeds
    1.85
     Norwich
    1.85
     Swansea
    1.79
     Southampton
    1.78
     Liverpool
    1.74
     Cardiff
    1.72
     Brisbane
    1.67
    Activations Density 0.014%

    No Known Activations