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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 15225
    Prev
    Next
    INDEX
    Explanations

    specific usage of the Latin phrase "per" in contexts related to following certain rules or traditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "per" used to indicate adherence to rules, traditions, or guidelines

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

    No Comments

    Negative Logits
     GOODMAN
    -0.85
    enegger
    -0.75
    MpServer
    -0.73
    ARDIS
    -0.71
    ForgeModLoader
    -0.68
     Lazarus
    -0.65
     Scholars
    -0.65
     Halls
    -0.63
     Plague
    -0.60
    çīĪ
    -0.60
    POSITIVE LOGITS
     capita
    1.30
    tains
    1.13
    ishable
    1.05
    malink
    1.04
    severe
    1.00
    missive
    0.99
    verting
    0.95
    secut
    0.94
    tained
    0.94
    secution
    0.93
    Activations Density 0.029%

    No Known Activations