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. 17863
    Prev
    Next
    INDEX
    Explanations

    phrases related to reflecting on or discussing various aspects of the term "pandering"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "panda" and its variants

    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
     Lauder
    -0.74
    pell
    -0.71
    FUL
    -0.64
    shock
    -0.64
    fully
    -0.63
     dstg
    -0.63
    terday
    -0.63
     Eisen
    -0.62
    LECT
    -0.58
     Jericho
    -0.58
    POSITIVE LOGITS
    emonium
    1.59
    emic
    1.45
    ering
    1.10
    emonic
    1.08
    erers
    1.06
    elines
    1.02
    erest
    0.96
    aren
    0.93
    emon
    0.93
    ered
    0.93
    Activations Density 0.036%

    No Known Activations