© 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. 9-RES-JB
    11. 10057
    Prev
    Next
    INDEX
    Explanations

    words related to issues, crimes, and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of authority and social media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otta
    -0.62
     teasp
    -0.60
     unto
    -0.57
    caliber
    -0.56
    ially
    -0.55
    xual
    -0.54
    to
    -0.54
    colored
    -0.53
    Ń·
    -0.51
     opin
    -0.51
    POSITIVE LOGITS
    ();
    0.56
    olphins
    0.55
     Hearthstone
    0.54
    ¶
    0.52
     ();
    0.52
    BBC
    0.52
    Merit
    0.51
     Whilst
    0.51
     Cisco
    0.51
     Nasa
    0.51
    Activations Density 1.176%

    No Known Activations