© 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. 11-RES-JB
    11. 21823
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of vengeance or revenge

    oai_token-act-pair · gpt-3.5-turbo

    words that relate to a specific type of concept or theme

    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
     writ
    -0.61
     unpublished
    -0.60
     downtime
    -0.60
     charism
    -0.60
     shortened
    -0.59
     fewer
    -0.59
     pronounce
    -0.58
     commissions
    -0.57
     owed
    -0.57
     born
    -0.57
    POSITIVE LOGITS
    arsity
    1.43
    anguard
    1.41
    ulture
    1.39
    oodoo
    1.34
    alkyrie
    1.32
    iking
    1.32
    aunted
    1.28
    itals
    1.27
    andals
    1.20
    enge
    1.18
    Activations Density 0.023%

    No Known Activations