© 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. 16663
    Prev
    Next
    INDEX
    Explanations

    references to news media outlets such as "The New York Times" or "The Guardian"

    oai_token-act-pair · gpt-3.5-turbo

    references to news publications or media 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
     stagn
    -0.73
     beware
    -0.72
     stopping
    -0.70
     extingu
    -0.70
    loading
    -0.69
    CVE
    -0.68
     slowing
    -0.68
    itures
    -0.67
     thrott
    -0.67
     leve
    -0.66
    POSITIVE LOGITS
     Huffington
    1.29
     Chronicle
    1.20
     Guardian
    1.19
     Daily
    1.14
     Verge
    1.12
     Economist
    1.11
     Associated
    1.10
    odor
    1.08
     Conversation
    1.07
     Observer
    1.04
    Activations Density 0.052%

    No Known Activations