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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 19642
    Prev
    Next
    INDEX
    Explanations

    phrases involving hip-hop culture

    oai_token-act-pair · gpt-3.5-turbo

    references to hip-hop culture and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.78
     QC
    -0.73
    ãĥŃ
    -0.71
     Wast
    -0.70
    ãĥŁ
    -0.69
    ãĤ¡
    -0.68
    fml
    -0.68
    venants
    -0.67
     Izan
    -0.63
     Reincarn
    -0.62
    POSITIVE LOGITS
    Adult
    0.68
    udic
    0.68
    worm
    0.67
    Hop
    0.66
    zik
    0.66
    bour
    0.65
    bery
    0.64
    eds
    0.63
    Jackson
    0.62
    roxy
    0.62
    Activations Density 0.170%

    No Known Activations