© 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. 4-RES-JB
    11. 22087
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "-ous" indicating full of, characterized by, possessing

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing negative qualities or severe characteristics

    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
     COURT
    -0.74
    elf
    -0.71
    enf
    -0.71
    é¾įå
    -0.66
    Board
    -0.65
    aver
    -0.65
    VPN
    -0.65
    oan
    -0.63
    foreseen
    -0.62
    ALT
    -0.62
    POSITIVE LOGITS
    Magikarp
    1.23
    ness
    1.02
    ous
    0.90
    nesses
    0.89
    ly
    0.87
     amounts
    0.87
    ity
    0.85
    lihood
    0.83
    ities
    0.80
     Kou
    0.78
    Activations Density 0.045%

    No Known Activations