Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8673
    Prev
    Next
    INDEX
    Explanations

    conjunctions "But" at the beginning of a sentence indicating a contrast or exception

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but"

    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
     segment
    -0.76
    sense
    -0.67
    heads
    -0.61
     period
    -0.61
     sense
    -0.61
     pier
    -0.60
     ceremony
    -0.60
     leg
    -0.58
    wall
    -0.58
     hor
    -0.58
    POSITIVE LOGITS
    tons
    1.13
    romeda
    1.05
     alas
    0.88
    theless
    0.85
    thodox
    0.79
    hra
    0.77
    withstanding
    0.76
    chers
    0.74
     Cummings
    0.73
    anamo
    0.73
    Activations Density 0.045%

    No Known Activations