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. 20790
    Prev
    Next
    INDEX
    Explanations

    pop culture references, particularly related to music and media

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pop music, particularly in various cultural contexts

    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
     witness
    -0.77
     attribution
    -0.68
     Ir
    -0.67
     prohibited
    -0.65
     ATI
    -0.65
     Tribune
    -0.64
     gloves
    -0.63
     obligated
    -0.63
     learned
    -0.63
     exemplary
    -0.63
    POSITIVE LOGITS
    pop
    4.46
    Pop
    2.31
     Pop
    1.87
     pop
    1.74
    population
    1.68
     POP
    1.63
    mop
    1.37
     pops
    1.21
    bub
    1.14
     popped
    1.06
    Activations Density 0.009%

    No Known Activations