© 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. 21640
    Prev
    Next
    INDEX
    Explanations

    terms related to technology companies and their products

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or concepts that involve the number two

    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
    pmwiki
    -0.78
    eston
    -0.64
    ogle
    -0.56
    activity
    -0.55
    humane
    -0.52
    rolog
    -0.52
     Transcript
    -0.51
    coal
    -0.51
     Corrections
    -0.51
    ople
    -0.51
    POSITIVE LOGITS
     apiece
    1.66
     totaling
    1.38
     simultaneously
    1.12
     consecut
    1.10
     respectively
    1.07
     concurrently
    1.01
     vying
    1.00
     separated
    0.99
    hips
    0.99
     viz
    0.96
    Activations Density 0.449%

    No Known Activations