© 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. 3086
    Prev
    Next
    INDEX
    Explanations

    mentions of media organizations and news publications

    oai_token-act-pair · gpt-3.5-turbo

    references to media ownership and control

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    ignty
    -0.70
    BIP
    -0.62
    pai
    -0.62
     balancing
    -0.62
    aterasu
    -0.61
    enary
    -0.60
     teamwork
    -0.60
     separ
    -0.59
     clasp
    -0.59
    POSITIVE LOGITS
     newspapers
    1.90
     tabloid
    1.72
     tabl
    1.70
     newspaper
    1.69
     Newsweek
    1.48
     news
    1.47
     News
    1.42
     magazines
    1.38
     Daily
    1.36
    ribune
    1.36
    Activations Density 0.945%

    No Known Activations