© 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. 7-RES-JB
    11. 20729
    Prev
    Next
    INDEX
    Explanations

    words related to proper names, more specifically names ending in 'on'

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPS
    -0.70
    ometimes
    -0.62
    æĸ¹
    -0.62
    eas
    -0.60
     compe
    -0.60
    RESULTS
    -0.60
     Clicker
    -0.60
    WHERE
    -0.59
    ãĤ¦
    -0.59
    enance
    -0.58
    POSITIVE LOGITS
    etheless
    1.17
    nen
    1.09
    auts
    1.06
    autical
    1.06
    cé
    1.05
    nect
    1.02
    ique
    0.98
    ews
    0.96
    aut
    0.96
    osuke
    0.94
    Activations Density 0.055%

    No Known Activations