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. 2003
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and injustices

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups affected by social issues

    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
    rawdownloadcloneembedreportprint
    -0.67
    tainment
    -0.66
    escription
    -0.66
    ibal
    -0.66
    heit
    -0.65
    iggurat
    -0.65
    arta
    -0.64
    onis
    -0.64
    atorium
    -0.63
    kamp
    -0.63
    POSITIVE LOGITS
     who
    1.36
     wishing
    1.13
    who
    1.11
     whom
    1.08
     whose
    1.02
     involved
    0.98
     pesky
    0.97
     entrusted
    0.97
     responsible
    0.97
     seeking
    0.95
    Activations Density 0.077%

    No Known Activations