© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22310
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "Death Star."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Death" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hof
    -0.72
    CN
    -0.71
    oyal
    -0.69
    oman
    -0.64
    ENCY
    -0.63
    atters
    -0.63
    OA
    -0.63
    ":["
    -0.61
    NEY
    -0.60
    DonaldTrump
    -0.60
    POSITIVE LOGITS
    blow
    1.26
    match
    1.20
    stroke
    1.08
    trap
    1.06
    claw
    1.00
    touch
    0.97
     Penalty
    0.96
     thro
    0.95
    spell
    0.93
    bringer
    0.91
    Activations Density 0.043%

    No Known Activations