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. 6-RES-JB
    6. 15999
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social media interactions and misunderstandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULTS
    -0.72
    uana
    -0.71
    phony
    -0.69
    pite
    -0.67
    metry
    -0.67
    idency
    -0.66
     millenn
    -0.62
    pine
    -0.62
    asio
    -0.61
    wives
    -0.61
    POSITIVE LOGITS
    ed
    2.05
    edIn
    1.44
    ing
    1.39
    edly
    1.27
    er
    1.06
    sites
    1.03
    ery
    1.01
    es
    0.98
    ers
    0.97
    esy
    0.96
    Activations Density 0.112%

    No Known Activations