© 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. 8-RES-JB
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    mentions of specific rappers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rappers and rap-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.80
    uckland
    -0.69
    thia
    -0.69
    lehem
    -0.68
     Manit
    -0.68
    ++++
    -0.67
    ++++++++++++++++
    -0.67
    licts
    -0.66
    arine
    -0.65
     Glou
    -0.64
    POSITIVE LOGITS
     Eminem
    0.90
     lyrics
    0.88
     lyric
    0.84
    ixtape
    0.79
    itone
    0.78
    efully
    0.77
     rapper
    0.77
     beats
    0.76
     Lamar
    0.75
     rappers
    0.74
    Activations Density 0.070%

    No Known Activations