© 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. 2962
    Prev
    Next
    INDEX
    Explanations

    the word "merely" used in a context of downplaying or diminishing significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "merely" to highlight dismissive or trivializing language

    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
    vals
    -0.68
    illas
    -0.66
     PLUS
    -0.65
     Conver
    -0.61
     Nurs
    -0.59
     UID
    -0.58
    erto
    -0.58
    ILL
    -0.57
    anon
    -0.57
    multipl
    -0.56
    POSITIVE LOGITS
    ifiable
    0.94
    rical
    0.88
     superficial
    0.80
     mortals
    0.77
    ional
    0.77
     incidental
    0.76
     cosmetic
    0.74
    hemer
    0.74
     guiActiveUn
    0.72
    iciary
    0.71
    Activations Density 0.033%

    No Known Activations