© 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. 20521
    Prev
    Next
    INDEX
    Explanations

    strong language expressing frustration or anger

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fuck" and its variations, often expressing strong emotion or emphasis

    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
    •layer 6 - anger

    No Comments

    Negative Logits
    BIL
    -0.74
    NetMessage
    -0.71
     rece
    -0.70
    ItemThumbnailImage
    -0.69
    PsyNetMessage
    -0.66
     screening
    -0.64
    Recomm
    -0.63
     conclud
    -0.62
     Scotia
    -0.62
     phyl
    -0.61
    POSITIVE LOGITS
    holes
    1.19
    hole
    1.14
    lord
    0.93
    bags
    0.92
    nuts
    0.91
    wit
    0.89
    fuck
    0.89
    opot
    0.86
    loads
    0.83
    glers
    0.83
    Activations Density 0.018%

    No Known Activations