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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3745
    Prev
    Next
    INDEX
    Explanations

    geographic locations related to a specific region or coast

    oai_token-act-pair · gpt-3.5-turbo

    references to specific coastal regions

    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
    -0.79
    chy
    -0.75
    interest
    -0.73
    rics
    -0.71
    cca
    -0.70
    inance
    -0.66
     externalToEVAOnly
    -0.66
    ãĥĬ
    -0.65
    VL
    -0.64
    sen
    -0.64
    POSITIVE LOGITS
     Coast
    1.10
     coast
    0.92
     Reserve
    0.80
     Coastal
    0.75
    opa
    0.73
    side
    0.73
     Guard
    0.73
    lake
    0.73
     Revival
    0.72
     coasts
    0.71
    Activations Density 0.005%

    No Known Activations