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. 4-RES-JB
    6. 19069
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating a lesser degree

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "less" in various contexts

    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
    Aren
    -0.79
     Properties
    -0.74
    Sky
    -0.71
    Grab
    -0.70
    TRY
    -0.69
    ULE
    -0.69
    Draft
    -0.68
    DK
    -0.68
    omnia
    -0.68
    DOM
    -0.68
    POSITIVE LOGITS
     than
    1.28
    thumbnails
    0.91
     forgiving
    0.89
     conspicuous
    0.89
    ened
    0.87
    than
    0.87
     stringent
    0.86
     aggressive
    0.83
    ening
    0.82
     intrusive
    0.82
    Activations Density 0.030%

    No Known Activations