© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5067
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to aiding or simplifying processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of facilitating or enabling processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shit
    -0.74
    guy
    -0.73
    wig
    -0.73
    kar
    -0.69
    boy
    -0.68
    bane
    -0.68
    berg
    -0.68
    thing
    -0.67
    tal
    -0.66
    thin
    -0.66
    POSITIVE LOGITS
     facilitating
    0.89
     facilitate
    0.82
     communication
    0.80
     medi
    0.73
     facilit
    0.72
     exporting
    0.72
     transporting
    0.71
     accessibility
    0.69
    ances
    0.68
     access
    0.68
    Activations Density 0.038%

    No Known Activations