© 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. 10-RES-JB
    11. 16937
    Prev
    Next
    INDEX
    Explanations

    words or phrases in languages other than English, likely related to a specific topic or context

    oai_token-act-pair · gpt-3.5-turbo

    words related to food or eating experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Damon
    -0.62
     Whale
    -0.62
     anonymity
    -0.60
     Wolverine
    -0.60
    advertisement
    -0.59
     minds
    -0.58
     Whitman
    -0.57
     Logged
    -0.56
     Hornets
    -0.56
     Lisp
    -0.55
    POSITIVE LOGITS
    ndum
    1.14
    nda
    1.03
    tic
    1.00
    til
    0.99
    si
    0.99
    º
    0.97
    rique
    0.96
    pter
    0.96
    tu
    0.96
    sis
    0.92
    Activations Density 0.101%

    No Known Activations