© 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. 8-RES-JB
    11. 3842
    Prev
    Next
    INDEX
    Explanations

    references related to awards or rewards, particularly those with the term "Pri" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to "prizes" or award-related terms

    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
    enegger
    -1.07
    schild
    -0.84
    lihood
    -0.70
    stead
    -0.69
    ORGE
    -0.66
    ded
    -0.66
     HELL
    -0.63
    ding
    -0.63
    bodied
    -0.63
    è¦ļéĨĴ
    -0.62
    POSITIVE LOGITS
    ests
    1.21
    zes
    1.11
    etary
    1.06
    eties
    1.04
    ety
    0.95
    esses
    0.94
    archs
    0.88
    Ľ
    0.88
    vy
    0.88
    eme
    0.88
    Activations Density 0.027%

    No Known Activations