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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 16109
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions and articles together

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating position or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efully
    -0.80
    Rather
    -0.75
    omever
    -0.75
    Likewise
    -0.74
    However
    -0.71
     accordingly
    -0.71
     Vaugh
    -0.70
     [*
    -0.70
    Those
    -0.70
    Neither
    -0.70
    POSITIVE LOGITS
     nutshell
    0.70
     Shutterstock
    0.69
     english
    0.65
     sale
    0.61
     WTC
    0.58
     americ
    0.57
     thumbnail
    0.57
     facebook
    0.57
     google
    0.56
     diagram
    0.55
    Activations Density 0.428%

    No Known Activations