© 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. 0-RES-JB
    11. 468
    Prev
    Next
    INDEX
    Explanations

    phrases related to mining activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mines, particularly in a context related to coal, uranium, or other resources

    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
     Breakfast
    -0.70
    package
    -0.67
    George
    -0.63
    Fri
    -0.63
    eway
    -0.62
     Hansen
    -0.62
    character
    -0.62
     Hispanic
    -0.61
    cial
    -0.61
     Trayvon
    -0.60
    POSITIVE LOGITS
     mines
    3.86
     Mines
    3.30
     Mine
    2.35
     mine
    1.96
    Mine
    1.87
    mine
    1.68
     mined
    1.68
     tunnels
    1.59
    mining
    1.55
     mining
    1.55
    Activations Density 0.019%

    No Known Activations