© 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. 8-RES-JB
    11. 17862
    Prev
    Next
    INDEX
    Explanations

    strong exclamations or emphasis in words

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or emphasis, particularly with the words "damn" and "darn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.97
    KY
    -0.77
    chn
    -0.71
    OHN
    -0.69
    ETF
    -0.66
    HCR
    -0.66
     Cosponsors
    -0.66
    Effect
    -0.65
    CRE
    -0.65
    idon
    -0.64
    POSITIVE LOGITS
    ibly
    0.84
     darn
    0.82
    nuts
    0.81
    ation
    0.78
    near
    0.78
    warm
    0.77
     damned
    0.77
     damn
    0.75
    orse
    0.72
    bugs
    0.72
    Activations Density 0.033%

    No Known Activations