© 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. 1-RES-JB
    11. 20053
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical coastlines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coastal locations

    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
    chel
    -0.87
    VL
    -0.76
    chy
    -0.72
    roma
    -0.69
     Flavoring
    -0.69
    inventory
    -0.67
    interest
    -0.66
    728
    -0.64
    etimes
    -0.63
    itsch
    -0.63
    POSITIVE LOGITS
     coast
    1.29
     shore
    0.94
     Coast
    0.90
     coastline
    0.87
     coasts
    0.83
     shores
    0.81
     unlaw
    0.79
     docks
    0.77
     dors
    0.74
    wreck
    0.74
    Activations Density 0.006%

    No Known Activations