© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 23241
    Prev
    Next
    INDEX
    Explanations

    commonly used transitional words signaling continuation or contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "still" and its usage in contexts indicating continuation or persistence despite challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ex
    -0.64
     signature
    -0.64
     20
    -0.63
     whistle
    -0.62
     bi
    -0.62
     authority
    -0.61
    âĢij
    -0.60
     ten
    -0.59
     Lib
    -0.59
     jun
    -0.58
    POSITIVE LOGITS
    Still
    3.45
     Still
    2.02
    Nevertheless
    1.85
    Nonetheless
    1.81
    still
    1.67
    Yet
    1.47
     Nonetheless
    1.43
    Already
    1.39
    Anyway
    1.37
    Regardless
    1.29
    Activations Density 0.007%

    No Known Activations