© 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. 10-RES-JB
    11. 16572
    Prev
    Next
    INDEX
    Explanations

    sentences containing the phrase "when it comes to"

    oai_token-act-pair · gpt-3.5-turbo

    references to a concept being discussed or evaluated in relation to various topics

    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
     Genius
    -0.64
     unchanged
    -0.59
     Waiting
    -0.57
    lime
    -0.55
    pour
    -0.54
    pause
    -0.53
     Amen
    -0.52
     Morse
    -0.51
     Rak
    -0.51
    cut
    -0.50
    POSITIVE LOGITS
     comes
    1.43
     mattered
    1.16
     Comes
    1.08
     matters
    1.07
     relates
    0.97
     came
    0.95
     arises
    0.95
     Matters
    0.89
    tains
    0.89
     suits
    0.87
    Activations Density 0.044%

    No Known Activations