© 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. 17783
    Prev
    Next
    INDEX
    Explanations

    superlative expressions indicating extreme experiences or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or experiences

    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
    gravity
    -0.62
    flix
    -0.61
     Mumbai
    -0.57
     Voyager
    -0.57
    resy
    -0.56
    papers
    -0.56
     Hau
    -0.56
    ensor
    -0.55
    uish
    -0.55
     deficit
    -0.54
    POSITIVE LOGITS
     ever
    1.31
     EVER
    1.24
     imaginable
    1.08
    ever
    0.97
     encountered
    0.88
     encount
    0.80
     Ever
    0.77
     feas
    0.77
     devised
    0.75
     anywhere
    0.73
    Activations Density 0.114%

    No Known Activations