© 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. 10-RES-JB
    11. 12497
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mere"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "mere" or reduced to something basic or trivial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Also
    -0.66
    also
    -0.65
    lees
    -0.64
    Cu
    -0.63
     particularly
    -0.63
     especially
    -0.63
     Purg
    -0.62
     Definitely
    -0.60
     definitely
    -0.59
    Crash
    -0.59
    POSITIVE LOGITS
     mortals
    1.29
     coincidence
    0.92
    ifiable
    0.92
     incidental
    0.84
     mortal
    0.77
     inconvenience
    0.76
    ified
    0.76
     curiosity
    0.76
    IFIED
    0.75
     fractions
    0.73
    Activations Density 0.026%

    No Known Activations