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. 1-RES-JB
    6. 18629
    Prev
    Next
    INDEX
    Explanations

    keywords related to the city of Bradford

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Bradford and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.82
    egal
    -0.78
    ozy
    -0.77
    tesy
    -0.76
    usp
    -0.72
    =]
    -0.70
    ccording
    -0.68
    vg
    -0.67
    phis
    -0.67
    >[
    -0.67
    POSITIVE LOGITS
     Bradford
    1.25
     Bridgewater
    0.88
    osaurus
    0.86
     Lancaster
    0.79
     Jarvis
    0.78
    ford
    0.77
     Palmer
    0.75
     Cutler
    0.72
     Hancock
    0.71
    ucci
    0.71
    Activations Density 0.005%

    No Known Activations