© 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. 16836
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations and allegations against individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accusations

    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
    til
    -0.78
    alde
    -0.73
    Tokens
    -0.71
     partName
    -0.70
    TPPStreamerBot
    -0.69
     Mehran
    -0.66
    udo
    -0.66
    readable
    -0.64
    hes
    -0.63
    then
    -0.63
    POSITIVE LOGITS
     wrongdoing
    0.83
     witchcraft
    0.82
     conspiring
    0.79
     misconduct
    0.78
     committing
    0.78
     delinqu
    0.76
     manslaughter
    0.75
     violating
    0.74
     perjury
    0.74
     murdering
    0.73
    Activations Density 0.057%

    No Known Activations