© 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. 8-RES-JB
    11. 6927
    Prev
    Next
    INDEX
    Explanations

    references to colonies

    oai_token-act-pair · gpt-3.5-turbo

    references to colonies and colonization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.87
    Downloadha
    -0.84
    inen
    -0.78
    gio
    -0.74
    iblings
    -0.74
    icago
    -0.73
    nesota
    -0.73
     Marketable
    -0.73
    eger
    -0.72
    itsch
    -0.71
    POSITIVE LOGITS
    eers
    0.91
     ship
    0.87
     outpost
    0.80
    mates
    0.78
     Colony
    0.78
     colonies
    0.74
     pigeon
    0.74
     ships
    0.73
     colony
    0.73
     colonists
    0.73
    Activations Density 0.058%

    No Known Activations