© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5376
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    the term "ge" and its variations, indicating a focus on geological concepts

    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
    iva
    -0.81
     Pupp
    -0.75
    esson
    -0.73
    SPONSORED
    -0.72
     Mandatory
    -0.70
    ivas
    -0.68
    aughs
    -0.68
    weeney
    -0.67
     Carry
    -0.67
    arers
    -0.65
    POSITIVE LOGITS
     ge
    3.57
     Ge
    2.10
     geo
    1.98
    Ge
    1.91
     geological
    1.84
     Geo
    1.62
     seism
    1.53
     geography
    1.51
     Geological
    1.50
    ge
    1.45
    Activations Density 0.011%

    No Known Activations