© 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. 20788
    Prev
    Next
    INDEX
    Explanations

    mentions of media, news, journalism, or reporting in a context involving some form of controversy or social issue

    oai_token-act-pair · gpt-3.5-turbo

    references to media, journalism, and related ethical concerns

    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
    BuyableInstoreAndOnline
    -0.84
    amac
    -0.79
     necklace
    -0.74
    ukong
    -0.74
    nants
    -0.73
    ciation
    -0.73
    ummer
    -0.70
    wcsstore
    -0.69
    borgh
    -0.69
    ãĤ©
    -0.69
    POSITIVE LOGITS
     journalism
    2.12
     journalistic
    1.99
     Journalism
    1.99
     journalists
    1.98
     Journalists
    1.94
     reporters
    1.81
     Pulitzer
    1.76
    journal
    1.71
     journalist
    1.64
     reporting
    1.64
    Activations Density 0.838%

    No Known Activations