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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 17548
    Prev
    Next
    INDEX
    Explanations

    the lowercase letter 't'

    oai_token-act-pair · gpt-3.5-turbo

    The negation of experiences or actions expressed through the word "haven't."

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

    No Comments

    Negative Logits
    Reviewer
    -0.79
    CVE
    -0.72
     disadvant
    -0.64
     behavi
    -0.63
     Piper
    -0.62
     SetTextColor
    -0.62
     Polaris
    -0.62
     Balkans
    -0.62
     lapt
    -0.60
    Anti
    -0.59
    POSITIVE LOGITS
    aken
    0.97
    alion
    0.95
    itles
    0.95
    otally
    0.95
    ween
    0.93
    weet
    0.90
    ribune
    0.89
    enegger
    0.89
    ople
    0.88
    ouched
    0.88
    Activations Density 0.029%

    No Known Activations