© 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. 17575
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting or explaining something in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    conditional or contrasting statements expressed through commas

    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
    iffe
    -0.83
    IER
    -0.76
    cia
    -0.69
    aky
    -0.66
    ss
    -0.64
    eni
    -0.63
     Became
    -0.61
    OME
    -0.61
    foreseen
    -0.61
    ¸
    -0.60
    POSITIVE LOGITS
     nor
    1.65
    nor
    1.24
     but
    1.10
     anymore
    1.07
     Nor
    1.04
    although
    0.97
     merely
    0.97
     though
    0.94
     either
    0.92
     necessarily
    0.92
    Activations Density 0.191%

    No Known Activations