© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17288
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "crystal"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "crystal."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Cosponsors
    -0.74
    ername
    -0.72
    hiro
    -0.71
    dit
    -0.69
    orship
    -0.69
    went
    -0.68
    chal
    -0.68
    ahime
    -0.68
    NER
    -0.67
    ij士
    -0.66
    POSITIVE LOGITS
    stal
    1.08
    stals
    1.07
     meth
    0.99
    igr
    0.95
     methamphetamine
    0.95
     crystals
    0.89
     quartz
    0.85
    isers
    0.81
    igrate
    0.80
    ciples
    0.79
    Activations Density 0.012%

    No Known Activations