© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20439
    Prev
    Next
    INDEX
    Explanations

    mentions of DJ's or DJ-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to DJs or disc jockeys within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    thritis
    -0.74
     Fas
    -0.71
    rights
    -0.70
     Wikimedia
    -0.68
    Attempts
    -0.64
    oldemort
    -0.64
    lust
    -0.64
     Nigeria
    -0.62
     Marketable
    -0.60
     Penguins
    -0.58
    POSITIVE LOGITS
     DJ
    1.19
    DJ
    1.18
     DJs
    0.98
     mixer
    0.89
    itone
    0.79
     dj
    0.78
     booth
    0.77
    MC
    0.69
    ilion
    0.67
     lapt
    0.67
    Activations Density 0.006%

    No Known Activations