© 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. 0-RES-JB
    11. 1365
    Prev
    Next
    INDEX
    Explanations

    phrases related to digging or investigating

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dig" or its variations

    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
    ayne
    -0.85
     Archdemon
    -0.71
    vals
    -0.69
    iah
    -0.65
    rette
    -0.62
     Winston
    -0.62
     Vanilla
    -0.62
    atus
    -0.62
     Procedures
    -0.62
     Caption
    -0.61
    POSITIVE LOGITS
     dig
    3.96
     digs
    2.25
     digging
    2.12
    Dig
    2.10
     Dig
    2.04
    dig
    2.03
     dug
    1.87
     excav
    1.62
     excavation
    1.38
     digest
    1.37
    Activations Density 0.024%

    No Known Activations