© 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. 20672
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or outcomes that may occur based on a preceding statement or condition

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "then," indicating a sequence or consequence in discussions

    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
    hab
    -0.79
    leneck
    -0.78
    forts
    -0.73
    avez
    -0.73
    hyde
    -0.72
    actionDate
    -0.72
    tyard
    -0.72
    olescent
    -0.71
    gest
    -0.71
    efe
    -0.69
    POSITIVE LOGITS
     surely
    1.27
     congratulations
    1.18
     why
    1.13
     yes
    1.07
     yeah
    1.05
     maybe
    0.96
     congr
    0.92
     perhaps
    0.91
     obviously
    0.88
     certainly
    0.84
    Activations Density 0.053%

    No Known Activations