© 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 EvalsExportsinterp-engineNEWAPI 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. 20347
    Prev
    Next
    INDEX
    Explanations

    terms related to pros and cons, advantages and disadvantages

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the benefits and risks associated with various subjects or topics

    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
    agne
    -0.80
    ixt
    -0.80
    sect
    -0.79
    married
    -0.75
     Shots
    -0.74
    fle
    -0.74
    TW
    -0.73
    agus
    -0.73
    atoon
    -0.72
    wat
    -0.72
    POSITIVE LOGITS
     disadvantages
    1.26
     drawbacks
    1.23
     affordability
    1.16
     liabilities
    1.14
     efficacy
    1.13
     effectiveness
    1.13
     usefulness
    1.11
     reliability
    1.11
     ethical
    1.07
    effic
    1.05
    Activations Density 0.455%

    No Known Activations