© 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. 6-RES-JB
    11. 1525
    Prev
    Next
    INDEX
    Explanations

    the word "Nonetheless" or "Nevertheless" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions or transitional phrases indicating contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otaur
    -0.66
    asus
    -0.66
    rador
    -0.64
     burg
    -0.64
    nec
    -0.61
    raz
    -0.61
    rals
    -0.60
    ipers
    -0.59
    amps
    -0.59
    aration
    -0.59
    POSITIVE LOGITS
    theless
    0.85
    chart
    0.76
     optimistic
    0.75
     upbeat
    0.74
     conclud
    0.74
     notwithstanding
    0.72
    noon
    0.71
     persisted
    0.69
     survives
    0.69
    heric
    0.69
    Activations Density 0.016%

    No Known Activations