© 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. 7-RES-JB
    11. 20871
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Anyway,"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anyway" and its variations, indicating a transition or change of topic in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solitary
    -0.68
    rive
    -0.67
    prus
    -0.61
    viol
    -0.59
     prost
    -0.59
    advert
    -0.58
    string
    -0.57
     simulated
    -0.57
    activated
    -0.56
    iably
    -0.56
    POSITIVE LOGITS
     Anyway
    0.91
    Anyway
    0.89
     congr
    0.79
     anyways
    0.78
    adays
    0.75
     ado
    0.74
     gotta
    0.72
     hurry
    0.72
     congratulations
    0.71
     NOTICE
    0.70
    Activations Density 0.034%

    No Known Activations