© 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. 10644
    Prev
    Next
    INDEX
    Explanations

    words related to antagonists, especially villains

    oai_token-act-pair · gpt-3.5-turbo

    references to villains in narratives or stories

    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
    galitarian
    -0.86
    ollen
    -0.75
    sterdam
    -0.74
    independent
    -0.74
    oday
    -0.72
    glas
    -0.72
    verett
    -0.71
    choes
    -0.70
    apers
    -0.69
    issance
    -0.69
    POSITIVE LOGITS
    ous
    1.17
    ously
    1.06
     villain
    1.00
     villains
    0.93
     mastermind
    0.92
     Bane
    0.88
    esses
    0.81
    ess
    0.77
    hattan
    0.76
    oid
    0.72
    Activations Density 0.018%

    No Known Activations