© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11523
    Prev
    Next
    INDEX
    Explanations

    references to popularity or widely recognized concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "popular" in various 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
    trace
    -0.75
     Assignment
    -0.73
    areth
    -0.72
    UGH
    -0.71
    asers
    -0.70
     Facility
    -0.69
    uci
    -0.67
    ectomy
    -0.66
     Controls
    -0.65
     Investigator
    -0.65
    POSITIVE LOGITS
     popular
    3.57
    popular
    2.69
     Popular
    2.02
     popularity
    1.80
     unpopular
    1.74
     famous
    1.59
     fashionable
    1.49
     trendy
    1.46
     widely
    1.40
     beloved
    1.37
    Activations Density 0.020%

    No Known Activations