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

    Neuronpedia

    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. 4-RES-JB
    11. 10396
    Prev
    Next
    INDEX
    Explanations

    news sources or articles tagged as "(Reuters)"

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and associated contextual elements in news articles

    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
    rew
    -0.90
    gram
    -0.68
    bags
    -0.65
     undergrad
    -0.65
    ibles
    -0.64
    worm
    -0.64
    tor
    -0.63
    houses
    -0.63
    ton
    -0.63
    alias
    -0.62
    POSITIVE LOGITS
    INESS
    0.86
     constitu
    0.79
     Seym
    0.76
    eka
    0.75
    IVES
    0.74
     tiss
    0.72
     Leban
    0.70
    esa
    0.70
    hester
    0.69
     âĶľ
    0.69
    Activations Density 0.036%

    No Known Activations