© 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. 11494
    Prev
    Next
    INDEX
    Explanations

    terms related to coal mining and fuel efficiency

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "a."

    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
     Avery
    -0.65
     band
    -0.62
    awa
    -0.62
     equ
    -0.60
    erman
    -0.60
     dist
    -0.59
     forecast
    -0.58
     Fisheries
    -0.57
     guides
    -0.57
     calibr
    -0.56
    POSITIVE LOGITS
     Palest
    0.82
     Wass
    0.78
    rarily
    0.75
    uania
    0.71
    issance
    0.71
    Downloadha
    0.68
     preval
    0.68
    ulia
    0.64
     thereof
    0.64
    MpServer
    0.63
    Activations Density 0.000%

    No Known Activations