© 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. 7-RES-JB
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    references to modern-day contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference contemporary society or modern life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -1.00
    edin
    -0.89
    ateral
    -0.81
     anecd
    -0.76
    unal
    -0.76
    ionics
    -0.72
     teasp
    -0.72
    agraph
    -0.71
    liga
    -0.70
    ately
    -0.70
    POSITIVE LOGITS
     slavery
    0.90
     incarnation
    0.88
     equivalents
    0.87
     version
    0.80
     relevance
    0.76
     Middle
    0.75
     Vatican
    0.74
     equivalent
    0.73
     versions
    0.73
     edition
    0.72
    Activations Density 0.023%

    No Known Activations