© 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. 10-RES-JB
    11. 18727
    Prev
    Next
    INDEX
    Explanations

    terms related to the element "carbon."

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon and related entities

    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
    CRIP
    -0.75
    Nap
    -0.68
     tomat
    -0.63
     Verse
    -0.59
     assum
    -0.59
    é¾įå¥ij士
    -0.58
     Constantin
    -0.57
     disparate
    -0.57
    urally
    -0.57
     Pione
    -0.57
    POSITIVE LOGITS
    celona
    1.31
    negie
    1.27
    bara
    1.24
    rier
    1.19
    riage
    1.14
    riors
    1.13
    bon
    1.07
    alyst
    1.05
    borough
    1.03
    hesda
    1.02
    Activations Density 0.049%

    No Known Activations