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. 10-RES-JB
    6. 19592
    Prev
    Next
    INDEX
    Explanations

    the word "but" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "But" indicating a contrast or transition in the narrative

    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
    obyl
    -0.94
    ãĥİ
    -0.75
    SourceFile
    -0.72
    ãģĨ
    -0.71
    dayName
    -0.69
    è¦ļéĨĴ
    -0.68
    ¯¯¯¯
    -0.67
    Synopsis
    -0.66
    ASED
    -0.65
    Fuck
    -0.65
    POSITIVE LOGITS
     critics
    1.16
     unlike
    1.00
     despite
    1.00
     proponents
    0.99
     campaigners
    0.94
     analysts
    0.93
     experts
    0.93
    tons
    0.92
     according
    0.89
     amid
    0.89
    Activations Density 0.122%

    No Known Activations