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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23313
    Prev
    Next
    INDEX
    Explanations

    proper nouns of cities

    oai_token-act-pair · gpt-3.5-turbo

    references to various cities

    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
     New
    -0.90
     P
    -0.90
     Qu
    -0.89
     T
    -0.89
     D
    -0.89
     Q
    -0.89
     L
    -0.88
     B
    -0.88
     M
    -0.88
     R
    -0.87
    POSITIVE LOGITS
    Portland
    1.71
    Denver
    1.71
    Michigan
    1.69
    Toronto
    1.66
    Sov
    1.64
    Philadelphia
    1.62
    Baltimore
    1.61
    Alabama
    1.61
    Ohio
    1.61
    Minnesota
    1.60
    Activations Density 0.093%

    No Known Activations