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. 0-RES-JB
    6. 17257
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Pop"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Pop" culture or the character "Iggy Pop."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ĭ
    -0.71
     depreciation
    -0.70
    aser
    -0.69
    azeera
    -0.68
    eth
    -0.68
    ulf
    -0.68
    yr
    -0.68
     UAE
    -0.67
     [&
    -0.67
    GH
    -0.67
    POSITIVE LOGITS
     Pop
    3.85
    Pop
    2.46
    pop
    2.28
     POP
    2.09
     pop
    2.08
     pops
    1.52
     Funk
    1.41
     Punk
    1.25
     Panic
    1.18
     popcorn
    1.16
    Activations Density 0.007%

    No Known Activations