Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 15244
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the location "York" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "York."

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

    No Comments

    Negative Logits
    cius
    -0.86
    aeda
    -0.71
    cedes
    -0.69
    ña
    -0.68
    htaking
    -0.67
    Oracle
    -0.67
    odcast
    -0.66
    hammad
    -0.66
     careful
    -0.65
    icio
    -0.65
    POSITIVE LOGITS
    town
    1.12
    dale
    1.00
    mares
    0.99
    mont
    0.89
    bean
    0.88
     City
    0.83
    burgh
    0.82
    stone
    0.79
    ville
    0.78
     Region
    0.77
    Activations Density 0.012%

    No Known Activations