© 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. 10-RES-JB
    11. 6914
    Prev
    Next
    INDEX
    Explanations

    postal codes and country names related to addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and its related addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apse
    -0.73
    commit
    -0.70
    iazep
    -0.69
    alin
    -0.66
    msg
    -0.65
    riz
    -0.63
    reath
    -0.62
    ashington
    -0.61
    atz
    -0.61
    zik
    -0.61
    POSITIVE LOGITS
     distributor
    1.06
     distributors
    0.98
     Customers
    0.98
     editions
    0.92
     localization
    0.92
     shores
    0.91
     markets
    0.89
     edition
    0.86
     locations
    0.86
     Distribution
    0.85
    Activations Density 0.219%

    No Known Activations