© 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. 2984
    Prev
    Next
    INDEX
    Explanations

    words related to a place called Rad

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Rad" in various contexts

    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
    ORTS
    -0.72
     gall
    -0.64
     htt
    -0.62
    redits
    -0.61
     roadside
    -0.60
     Briggs
    -0.60
     bounds
    -0.58
     Rowling
    -0.58
     gracious
    -0.57
    urities
    -0.57
    POSITIVE LOGITS
    iance
    1.30
    iated
    1.26
    cliffe
    1.24
    iation
    1.23
    isson
    1.17
    icals
    1.17
    iate
    1.16
    iol
    1.16
    iant
    1.13
    iants
    1.12
    Activations Density 0.021%

    No Known Activations