© 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. 17692
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific individual named "Gar" along with variations of the name

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gar."

    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
    terday
    -0.91
    ĨĴ
    -0.81
     CPC
    -0.71
    ĸļ
    -0.68
    llers
    -0.67
    vironment
    -0.66
     newsp
    -0.66
    orld
    -0.62
     seeker
    -0.62
     Mutual
    -0.59
    POSITIVE LOGITS
    bage
    1.47
    rets
    1.09
    lean
    1.06
    rier
    1.02
    neau
    1.02
    leans
    0.98
    riott
    0.93
    riers
    0.93
    bled
    0.92
    rett
    0.87
    Activations Density 0.027%

    No Known Activations