© 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. 9214
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of declaring someone dead

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pronounced" related to death or medical declarations

    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
    izons
    -0.70
     Camer
    -0.70
    ionage
    -0.69
    href
    -0.69
    allow
    -0.68
    ansas
    -0.68
     Territories
    -0.67
     Reprodu
    -0.66
    adr
    -0.65
    ottage
    -0.65
    POSITIVE LOGITS
     pronunciation
    0.94
     pronounce
    0.91
     deaf
    0.87
     pronounced
    0.86
    unci
    0.82
     spelling
    0.81
     conson
    0.80
    ysis
    0.78
     vowel
    0.77
     fluent
    0.76
    Activations Density 0.027%

    No Known Activations