© 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. 2-RES-JB
    11. 759
    Prev
    Next
    INDEX
    Explanations

    the word "nonetheless"

    oai_token-act-pair · gpt-4-turbo

    conjunctive adverbs or transitional phrases like "nevertheless."

    oai_token-act-pair · gpt-3.5-turbo

    the word "nonetheless" and its variants, indicating a contrast or continuation despite obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raz
    -0.71
     Roses
    -0.68
    nec
    -0.66
    onz
    -0.66
    """
    -0.64
    chuk
    -0.64
    enter
    -0.61
    azine
    -0.60
     Hunting
    -0.60
    asus
    -0.60
    POSITIVE LOGITS
     nonetheless
    0.98
    theless
    0.98
    etheless
    0.93
    xual
    0.89
    NESS
    0.86
     nevertheless
    0.85
     mirac
    0.80
     somehow
    0.79
    wcs
    0.77
     challeng
    0.75
    Activations Density 0.004%

    No Known Activations