© 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. 9-RES-JB
    11. 10053
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rat" or derivatives like "rating"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "rat" or "Rat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.77
    conservancy
    -0.75
    Ļ½
    -0.68
     Mandela
    -0.68
     Marketplace
    -0.63
    «ĺ
    -0.63
     Cyprus
    -0.63
     instantaneous
    -0.61
    alach
    -0.59
     Papua
    -0.59
    POSITIVE LOGITS
    chet
    1.57
    che
    1.12
    cliffe
    1.09
    ting
    1.02
    atos
    0.89
    ty
    0.86
    ename
    0.86
    rice
    0.86
    cher
    0.86
    chery
    0.85
    Activations Density 0.028%

    No Known Activations