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

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21795
    Prev
    Next
    INDEX
    Explanations

    the word "but" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrast or opposition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.74
     gy
    -0.72
     commencement
    -0.71
     orientation
    -0.67
     cage
    -0.67
     reef
    -0.66
     ceremony
    -0.65
     preparation
    -0.63
     segment
    -0.63
    uum
    -0.62
    POSITIVE LOGITS
    tons
    1.21
    theless
    1.20
    minus
    1.15
    etheless
    1.00
     alas
    0.90
    but
    0.84
    terday
    0.84
    tery
    0.81
    withstanding
    0.80
    gettable
    0.79
    Activations Density 0.009%

    No Known Activations