© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22004
    Prev
    Next
    INDEX
    Explanations

    references to the term "Monster"

    oai_token-act-pair · gpt-3.5-turbo

    characters or elements related to a specific fictional monster or creature

    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
     ETF
    -0.74
     indent
    -0.68
     omission
    -0.63
     scraping
    -0.62
     infer
    -0.58
     dividends
    -0.58
    BW
    -0.57
     straw
    -0.57
     exclusion
    -0.56
     stewards
    -0.55
    POSITIVE LOGITS
    opol
    0.83
    onic
    0.81
    ropolis
    0.80
    rals
    0.73
    atari
    0.72
    onia
    0.72
    hao
    0.70
    oras
    0.69
    soon
    0.69
    atra
    0.68
    Activations Density 0.093%

    No Known Activations