Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15478
    Prev
    Next
    INDEX
    Explanations

    single words and phrases related to rebellion or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to "counter" concepts or movements

    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
    OOD
    -0.67
     goodbye
    -0.64
     Forge
    -0.63
     Franks
    -0.61
     Finch
    -0.61
     Slime
    -0.60
     Tornado
    -0.60
     Bram
    -0.60
    icity
    -0.59
     Bib
    -0.58
    POSITIVE LOGITS
    measures
    1.47
    balance
    1.38
    intuitive
    1.38
    attack
    1.31
    fact
    1.25
    clock
    1.24
    culture
    1.23
    offensive
    1.22
    intelligence
    1.22
    cultural
    1.21
    Activations Density 0.019%

    No Known Activations