© 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. 10-RES-JB
    11. 6481
    Prev
    Next
    INDEX
    Explanations

    prepositions describing movement onto a surface or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement or transition onto a surface or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.85
    sense
    -0.73
    SOURCE
    -0.67
    shaw
    -0.66
     sexes
    -0.65
    DEN
    -0.64
     indo
    -0.63
    âĨij
    -0.62
    rw
    -0.61
    resp
    -0.60
    POSITIVE LOGITS
     behalf
    1.04
     unsuspecting
    0.98
     shelves
    0.97
     rooft
    0.85
     campuses
    0.84
     campus
    0.84
     unwitting
    0.77
    screen
    0.76
     waivers
    0.74
     racks
    0.74
    Activations Density 0.030%

    No Known Activations