© 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. 7-RES-JB
    11. 20735
    Prev
    Next
    INDEX
    Explanations

    situations or topics for discussion with some level of complexity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a change in topic or transition in discussion

    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
     Maintenance
    -0.64
     wheelchair
    -0.57
    tein
    -0.55
     Basics
    -0.55
     assisted
    -0.53
     Sims
    -0.52
     Gamble
    -0.51
     Equipment
    -0.51
     maintenance
    -0.51
     HI
    -0.50
    POSITIVE LOGITS
    etheless
    0.87
     insur
    0.75
    .).
    0.66
     imaginable
    0.63
     prophetic
    0.62
     geopolitical
    0.62
    .</
    0.62
    political
    0.61
    tains
    0.61
     unfolding
    0.60
    Activations Density 1.505%

    No Known Activations