© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9622
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "or" as a conjunction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternatives or options, typically in a conditional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emi
    -0.72
    estro
    -0.67
    onday
    -0.65
    ires
    -0.65
    ETS
    -0.64
    orter
    -0.62
    ursday
    -0.62
    IDENT
    -0.61
    KER
    -0.60
    owner
    -0.60
    POSITIVE LOGITS
     alternatively
    1.34
    chard
    1.07
     else
    1.00
    Else
    0.99
     maybe
    0.95
    acular
    0.94
     whatever
    0.93
    nery
    0.92
     perhaps
    0.90
     worse
    0.88
    Activations Density 0.070%

    No Known Activations