© 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. 19362
    Prev
    Next
    INDEX
    Explanations

    news-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to news events or announcements

    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
    asus
    -0.77
    orney
    -0.71
    asse
    -0.71
    amiya
    -0.67
    atos
    -0.67
    orsi
    -0.66
    ¯¯
    -0.66
    rylic
    -0.65
    inho
    -0.65
    ength
    -0.64
    POSITIVE LOGITS
    worthiness
    1.14
    worthy
    1.10
    flash
    1.03
    reader
    1.00
    room
    0.84
     announcement
    0.83
     announcements
    0.80
     headlines
    0.78
     RELEASE
    0.78
    print
    0.78
    Activations Density 0.035%

    No Known Activations