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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12772
    Prev
    Next
    INDEX
    Explanations

    terms related to precious metals like gold, silver, and copper

    oai_token-act-pair · gpt-3.5-turbo

    references to specific operations or processes related to metals and minerals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Keefe
    -0.93
    habi
    -0.90
    widget
    -0.81
    awk
    -0.79
    Reilly
    -0.79
     dispatcher
    -0.78
     parenting
    -0.76
    EStreamFrame
    -0.75
    beh
    -0.75
    Walker
    -0.75
    POSITIVE LOGITS
     gold
    1.68
     metals
    1.68
     diamonds
    1.63
     copper
    1.60
     mineral
    1.57
     stones
    1.56
     minerals
    1.56
     diamond
    1.56
    Gold
    1.56
     Gold
    1.49
    Activations Density 0.282%

    No Known Activations