Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14506
    Prev
    Next
    INDEX
    Explanations

    words related to scientific instruments, particularly microscopes and detectors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific instruments and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arat
    -0.73
    Days
    -0.70
    stitial
    -0.69
     Summers
    -0.68
    mes
    -0.68
     Slaughter
    -0.67
    ownt
    -0.67
    astical
    -0.66
    styles
    -0.66
    ros
    -0.66
    POSITIVE LOGITS
     detector
    2.60
     interpreter
    2.14
     microscope
    2.12
     detectors
    2.06
     telescope
    1.94
     scanner
    1.81
     translator
    1.73
     projector
    1.73
     calculator
    1.69
     recorder
    1.66
    Activations Density 0.062%

    No Known Activations