© 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. 0-RES-JB
    11. 2467
    Prev
    Next
    INDEX
    Explanations

    words related to spoilers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spoil" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lication
    -0.97
     meditation
    -0.85
    MRI
    -0.82
    chart
    -0.73
    IST
    -0.72
    rouch
    -0.72
     Gallup
    -0.72
     Meditation
    -0.69
     CPR
    -0.69
    itness
    -0.69
    POSITIVE LOGITS
     spo
    3.82
     spoil
    3.60
     spoiled
    3.44
     Spo
    1.68
     spoilers
    1.65
     spoiler
    1.58
     wast
    1.30
     ruined
    1.30
     ruining
    1.28
     rotten
    1.28
    Activations Density 0.043%

    No Known Activations