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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13894
    Prev
    Next
    INDEX
    Explanations

    mentions of news hosts and political figures in conversations

    oai_token-act-pair · gpt-3.5-turbo

    references to news anchors and their interactions on various news programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.96
     signatures
    -0.77
    PDF
    -0.77
    dylib
    -0.73
     parcels
    -0.72
    ICT
    -0.72
     Agric
    -0.71
     Grimoire
    -0.70
     Cth
    -0.69
    steam
    -0.69
    POSITIVE LOGITS
     MSNBC
    1.78
     CNN
    1.50
     Hannity
    1.47
    CNN
    1.43
     anchor
    1.34
     CNBC
    1.32
     host
    1.32
     anchors
    1.30
     hosts
    1.23
     NBC
    1.21
    Activations Density 0.557%

    No Known Activations