© 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. 6-RES-JB
    11. 12834
    Prev
    Next
    INDEX
    Explanations

    actions involving movement or physical activity

    oai_token-act-pair · gpt-3.5-turbo

    instances and descriptions of sexual or intimate interactions

    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
    ador
    -0.53
     Historically
    -0.51
     srfN
    -0.51
     Nielsen
    -0.50
     historically
    -0.50
     nowadays
    -0.49
     spoilers
    -0.49
     depends
    -0.49
     lately
    -0.48
     Previous
    -0.48
    POSITIVE LOGITS
    later
    0.59
     again
    0.57
    Reloaded
    0.56
     exting
    0.55
    quit
    0.55
    CONCLUS
    0.54
    cffffcc
    0.54
    ADRA
    0.54
    CLASSIFIED
    0.54
    FG
    0.54
    Activations Density 1.615%

    No Known Activations