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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17468
    Prev
    Next
    INDEX
    Explanations

    content related to news headlines and articles

    oai_token-act-pair · gpt-3.5-turbo

    text structures or markers often used in articles, such as headings or story continuations

    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
     heights
    -0.67
     shader
    -0.62
     gems
    -0.61
     waking
    -0.60
     exerc
    -0.59
     DG
    -0.59
     colours
    -0.58
     grounding
    -0.58
     laying
    -0.58
    papers
    -0.58
    POSITIVE LOGITS
     Continued
    0.97
    ccording
    0.96
     WATCHED
    0.91
    Photos
    0.81
    ogether
    0.78
    Read
    0.75
     Expand
    0.75
    zens
    0.74
    htaking
    0.74
     Asked
    0.73
    Activations Density 0.198%

    No Known Activations