© 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. 12-RES-JB
    11. 4172
    Prev
    Next
    INDEX
    Explanations

    mentions of news network names, specifically "CBS 9" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific news organizations, particularly CBS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    yip
    -0.72
     thrust
    -0.60
     maiden
    -0.60
    holders
    -0.59
     Blumenthal
    -0.59
     langu
    -0.59
    istry
    -0.58
    board
    -0.58
     Uriel
    -0.55
    boarding
    -0.55
    POSITIVE LOGITS
     Evening
    1.08
    Sports
    1.06
    Denver
    0.92
    DF
    0.90
    Chicago
    0.88
     News
    0.87
    News
    0.84
    Miami
    0.84
     Interactive
    0.83
    NEWS
    0.79
    Activations Density 0.018%

    No Known Activations