© 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. 7779
    Prev
    Next
    INDEX
    Explanations

    titles and names of various media works or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to music albums and related experiences

    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
     referen
    -0.83
     outsourcing
    -0.79
     carbohyd
    -0.76
     volunte
    -0.75
     terminology
    -0.74
     housing
    -0.74
     hypot
    -0.73
     instit
    -0.73
     benches
    -0.73
     sponsoring
    -0.72
    POSITIVE LOGITS
     Trilogy
    1.22
     Reborn
    1.18
     Remix
    1.03
     Ruin
    1.03
     Deadly
    1.02
     Nights
    1.01
     Dreams
    1.01
     Records
    1.00
     Thieves
    0.98
     Forever
    0.97
    Activations Density 0.298%

    No Known Activations