© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13707
    Prev
    Next
    INDEX
    Explanations

    updates and announcements within text

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or announcements

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

    No Comments

    Negative Logits
    inki
    -0.82
    ogie
    -0.79
    utical
    -0.78
    ateurs
    -0.77
    advant
    -0.74
    urat
    -0.74
    ophers
    -0.71
    quartered
    -0.71
    vey
    -0.70
    ogly
    -0.69
    POSITIVE LOGITS
     updates
    0.76
     timestamp
    0.76
     news
    0.72
     rc
    0.71
     VERS
    0.70
     notification
    0.69
     Version
    0.69
     Updates
    0.68
     dawn
    0.68
     delet
    0.67
    Activations Density 0.145%

    No Known Activations