© 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. 11-RES-JB
    11. 15731
    Prev
    Next
    INDEX
    Explanations

    references to historical events and colonization

    oai_token-act-pair · gpt-3.5-turbo

    historical references to transportation and supplies

    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
    gencies
    -0.86
     NCT
    -0.80
     HRC
    -0.78
     unfocusedRange
    -0.77
    xual
    -0.76
    zza
    -0.75
     Whedon
    -0.75
    ionics
    -0.74
    ibling
    -0.74
    respective
    -0.74
    POSITIVE LOGITS
     explorers
    1.71
     colonists
    1.65
     settlers
    1.63
     colonization
    1.46
     explorer
    1.41
     voyage
    1.36
     missionaries
    1.34
     enslaved
    1.29
     conqu
    1.26
     pioneers
    1.25
    Activations Density 0.356%

    No Known Activations