© 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. 8-RES-JB
    11. 10382
    Prev
    Next
    INDEX
    Explanations

    words related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    important adjectives that signify significance or prominence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pledge
    -0.62
    earance
    -0.61
     fly
    -0.60
     bat
    -0.58
     itch
    -0.57
     temper
    -0.57
     crawl
    -0.57
     shave
    -0.57
    ynthesis
    -0.57
     fight
    -0.56
    POSITIVE LOGITS
    aneously
    1.19
     enough
    1.06
    ally
    0.97
    ially
    0.95
    ised
    0.91
    ALLY
    0.89
    ly
    0.88
    handedly
    0.87
    inently
    0.85
    arily
    0.85
    Activations Density 0.346%

    No Known Activations