© 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. 8-RES-JB
    11. 19274
    Prev
    Next
    INDEX
    Explanations

    phrases related to career changes or advancements

    oai_token-act-pair · gpt-3.5-turbo

    references to awards or accolades

    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
     psi
    -0.79
     Saint
    -0.71
     PS
    -0.70
     Plane
    -0.70
     PlayStation
    -0.69
     nano
    -0.69
     Pizza
    -0.69
     pra
    -0.69
     Pi
    -0.69
     Playstation
    -0.68
    POSITIVE LOGITS
    ad
    1.56
    ads
    1.35
    AD
    1.31
    adian
    1.25
    adic
    1.15
    adi
    1.10
    adal
    1.09
    ada
    1.07
    aid
    1.06
    ado
    1.05
    Activations Density 0.214%

    No Known Activations