© 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. 8-RES-JB
    11. 4131
    Prev
    Next
    INDEX
    Explanations

    phrases related to occupying or taking up space

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time management and spatial constraints

    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
    MpServer
    -0.88
    FORE
    -0.75
    aret
    -0.71
    ISA
    -0.71
    Co
    -0.65
    istar
    -0.65
    cision
    -0.64
    ACA
    -0.63
    >>>
    -0.63
    onduct
    -0.61
    POSITIVE LOGITS
     shelves
    1.08
     memory
    1.02
     lungs
    0.94
     inbox
    0.90
     notebooks
    0.88
     drawer
    0.86
     gul
    0.85
     mind
    0.85
     pores
    0.85
     folders
    0.84
    Activations Density 0.614%

    No Known Activations