© 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. 0-RES-JB
    11. 8234
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "journalism"

    oai_token-act-pair · gpt-3.5-turbo

    references to journalism and its various aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roid
    -0.75
    strong
    -0.68
    loc
    -0.65
    edes
    -0.63
     unloaded
    -0.60
    Item
    -0.60
    chy
    -0.58
    OLD
    -0.58
    rix
    -0.58
     unused
    -0.57
    POSITIVE LOGITS
     journalism
    3.79
     Journalism
    2.80
     journalistic
    2.23
     journalists
    1.86
     Journalists
    1.85
     journalist
    1.65
    journal
    1.42
     storytelling
    1.38
     photography
    1.31
     filmmaking
    1.28
    Activations Density 0.017%

    No Known Activations