© 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. 7-RES-JB
    11. 1837
    Prev
    Next
    INDEX
    Explanations

    mentions of gemstones

    oai_token-act-pair · gpt-3.5-turbo

    references to gemstones

    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
     reps
    -0.65
     Parties
    -0.65
    ŃĶ
    -0.65
     AVG
    -0.64
     Carly
    -0.63
     Pace
    -0.63
     Roose
    -0.62
     Abstract
    -0.62
     Grounds
    -0.62
    lihood
    -0.59
    POSITIVE LOGITS
    stones
    1.42
    stone
    1.33
    cit
    0.89
     gems
    0.88
    cellent
    0.84
     gem
    0.83
    bl
    0.83
    oche
    0.80
    onse
    0.80
    bard
    0.80
    Activations Density 0.025%

    No Known Activations