© 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. 10-RES-JB
    11. 1199
    Prev
    Next
    INDEX
    Explanations

    mentions of media, journalism, and press-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to journalism and related media topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amac
    -0.82
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.79
    nants
    -0.73
    ciation
    -0.73
     Enchant
    -0.73
    BuyableInstoreAndOnline
    -0.72
    borgh
    -0.71
    Ĥª
    -0.71
    ŃĶ
    -0.70
    emp
    -0.68
    POSITIVE LOGITS
     journalism
    2.08
     journalistic
    2.03
     Journalism
    1.78
     journalists
    1.76
     Journalists
    1.68
     editorial
    1.67
     reporters
    1.62
     reporting
    1.57
     newspapers
    1.55
     editors
    1.54
    Activations Density 0.688%

    No Known Activations