© 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. 2-RES-JB
    11. 17858
    Prev
    Next
    INDEX
    Explanations

    mentions of settler-related terms like settlers, settlement, and outpost

    oai_token-act-pair · gpt-3.5-turbo

    references to settlers and settlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reditary
    -0.90
    abol
    -0.89
    otom
    -0.81
    emort
    -0.81
    ocket
    -0.79
    otine
    -0.79
    hift
    -0.79
    inx
    -0.78
    emis
    -0.77
    cemic
    -0.76
    POSITIVE LOGITS
     settlers
    1.03
     settlements
    1.00
     sett
    0.95
     Settlement
    0.93
     outpost
    0.82
     Sett
    0.82
     encamp
    0.81
     settlement
    0.76
     Doodle
    0.74
     Ariel
    0.74
    Activations Density 0.012%

    No Known Activations