© 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. 10-RES-JB
    11. 11525
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions, particularly "and" and "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laughs
    -0.71
    ogo
    -0.71
    uta
    -0.70
    was
    -0.70
    igr
    -0.66
     Was
    -0.66
    tains
    -0.65
    onica
    -0.65
    uts
    -0.64
     WAS
    -0.63
    POSITIVE LOGITS
     are
    1.58
     aren
    1.43
     deserve
    1.28
     have
    1.26
     they
    1.19
     require
    1.17
     constitute
    1.15
     appear
    1.13
     were
    1.13
     rely
    1.12
    Activations Density 0.448%

    No Known Activations