© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6875
    Prev
    Next
    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that reference emotions or emotional expressions

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

    No Comments

    Negative Logits
     rall
    -0.92
     mosqu
    -0.86
     glim
    -0.84
     challeng
    -0.81
     defe
    -0.81
     notor
    -0.78
     undermin
    -0.77
    onga
    -0.75
     enthusi
    -0.74
     crabs
    -0.73
    POSITIVE LOGITS
     Retrieved
    1.25
     Includes
    1.23
     However
    1.17
     Whilst
    1.15
     Also
    1.11
     While
    1.11
     Accessed
    1.09
     They
    1.09
     Additionally
    1.08
     Please
    1.08
    Activations Density 0.757%

    No Known Activations