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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2237
    Prev
    Next
    INDEX
    Explanations

    words related to migration and movement of people or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to movement or change in population dynamics

    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
     Tennis
    -0.65
     BAR
    -0.64
    lock
    -0.64
    imon
    -0.61
     Marks
    -0.59
     Parts
    -0.58
    Ãī
    -0.57
    orno
    -0.56
    é
    -0.56
     taped
    -0.56
    POSITIVE LOGITS
     influx
    3.47
     exodus
    1.91
     infusion
    1.74
     uptick
    1.51
     surge
    1.39
     onslaught
    1.36
     flux
    1.27
     migration
    1.23
     arrivals
    1.20
     overflow
    1.18
    Activations Density 0.009%

    No Known Activations