© 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 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. 8-RES-JB
    11. 11124
    Prev
    Next
    INDEX
    Explanations

    newspaper names containing the word "Herald."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific newspapers or news outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chwitz
    -0.87
    achev
    -0.82
    different
    -0.76
     theirs
    -0.72
     ours
    -0.72
    facebook
    -0.72
    milo
    -0.71
    stretched
    -0.70
    imilar
    -0.70
     hers
    -0.70
    POSITIVE LOGITS
     Editorial
    1.24
     Tribune
    1.16
     Newspaper
    1.09
     newspaper
    1.03
     Herald
    1.03
     Newsp
    1.02
     columnist
    1.01
     editorial
    0.96
     Dispatch
    0.95
     Gazette
    0.93
    Activations Density 0.105%

    No Known Activations