© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    terms related to stealing or unlawfully taking possessions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theft or robbery, particularly looting and plundering

    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
    ioxide
    -0.69
     constitu
    -0.69
    Temperature
    -0.68
    thood
    -0.68
    BRE
    -0.67
     antigen
    -0.66
    cond
    -0.65
    GHz
    -0.64
     Berks
    -0.64
     PAT
    -0.63
    POSITIVE LOGITS
    ibrary
    1.02
     looted
    0.97
     loot
    0.97
     crates
    0.87
    owship
    0.85
     piles
    0.83
     trove
    0.80
     boxes
    0.78
     spo
    0.78
     carts
    0.76
    Activations Density 0.029%

    No Known Activations