© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 22318
    Prev
    Next
    INDEX
    Explanations

    words related to "Crystal"

    oai_token-act-pair · gpt-3.5-turbo

    references to 'crystal' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.73
    gets
    -0.73
    went
    -0.71
    iannopoulos
    -0.71
    orship
    -0.67
    NER
    -0.67
    tie
    -0.67
     McGr
    -0.64
    kers
    -0.63
     unrestricted
    -0.63
    POSITIVE LOGITS
     meth
    1.08
    stal
    1.01
    stals
    0.93
     violet
    0.91
     methamphetamine
    0.85
     Gems
    0.85
    ized
    0.84
     clear
    0.82
    Disk
    0.80
    ãĤ©
    0.76
    Activations Density 0.042%

    No Known Activations