© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14638
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds and scientific terminology

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.89
    isha
    -0.67
    trak
    -0.66
     Celsius
    -0.63
    ensional
    -0.62
     stiffness
    -0.62
     Shank
    -0.59
     Cheong
    -0.58
    frames
    -0.58
    pad
    -0.57
    POSITIVE LOGITS
    CLE
    0.78
    cious
    0.70
    atible
    0.70
    stal
    0.69
    ulhu
    0.68
    aneous
    0.68
    atl
    0.67
    ioxide
    0.67
    uration
    0.67
    ãĤ¼ãĤ¦ãĤ¹
    0.66
    Activations Density 0.235%

    No Known Activations