© 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. 11-RES-JB
    11. 7833
    Prev
    Next
    INDEX
    Explanations

    descriptions of various types of geographical features, such as hills, mountains, cliffs, valleys, and slopes

    oai_token-act-pair · gpt-3.5-turbo

    geographical features and landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.74
     Emails
    -0.72
     Token
    -0.66
    Transaction
    -0.66
     Ticket
    -0.63
    ership
    -0.63
     Registry
    -0.62
     Pulse
    -0.62
    ticket
    -0.62
    ploy
    -0.61
    POSITIVE LOGITS
     overlooking
    1.34
    ides
    1.20
     slopes
    1.17
     bordering
    1.08
     dotted
    1.04
    ipel
    1.02
     slope
    1.00
     surrounding
    0.99
    cape
    0.99
     cliffs
    0.97
    Activations Density 0.266%

    No Known Activations