© 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. 2-RES-JB
    11. 7906
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific news outlet or publication

    oai_token-act-pair · gpt-3.5-turbo

    references to the news outlet "The Daily Beast" and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.72
    benefit
    -0.67
    peat
    -0.65
    bodied
    -0.65
     scrim
    -0.64
    depend
    -0.64
    Äĩ
    -0.64
    ced
    -0.63
    together
    -0.63
    hold
    -0.62
    POSITIVE LOGITS
     ARTICLE
    0.90
     columnist
    0.87
     Editorial
    0.86
    Magazine
    0.81
     VIDEOS
    0.81
     editor
    0.79
    £ı
    0.79
     editorial
    0.77
     inacc
    0.76
     Editors
    0.75
    Activations Density 0.315%

    No Known Activations