© 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. 8-RES-JB
    11. 20438
    Prev
    Next
    INDEX
    Explanations

    keywords related to news stories or article highlights

    oai_token-act-pair · gpt-3.5-turbo

    references to narrative highlights or story elements

    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
     sulph
    -0.68
    ãĥĺãĥ©
    -0.66
    İĭ
    -0.64
    essage
    -0.64
    ergic
    -0.64
    »Ĵ
    -0.63
    agles
    -0.63
     stocking
    -0.62
    wcsstore
    -0.62
    agall
    -0.60
    POSITIVE LOGITS
    telling
    1.12
     Transcript
    0.91
    line
    0.88
     Story
    0.86
    stal
    0.80
     highlights
    0.79
    bold
    0.78
     Reporter
    0.78
     Details
    0.78
     Highlights
    0.76
    Activations Density 0.019%

    No Known Activations