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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 10321
    Prev
    Next
    INDEX
    Explanations

    mentions of things or actions being popular

    oai_token-act-pair · gpt-3.5-turbo

    the concept of popularity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thur
    -0.88
     Aviv
    -0.74
    heed
    -0.73
    aca
    -0.70
    ouls
    -0.69
    ander
    -0.69
     Kear
    -0.68
    aul
    -0.65
     Centauri
    -0.64
    cule
    -0.64
    POSITIVE LOGITS
    popular
    1.20
     popular
    1.11
     Popular
    0.85
    rities
    0.80
    iatus
    0.73
     favourite
    0.72
    ity
    0.71
     unpopular
    0.70
    ised
    0.69
     circulation
    0.68
    Activations Density 0.016%

    No Known Activations