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

    Neuronpedia

    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. 17845
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to persons or places in news articles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names of individuals connected to various events

    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
    Anyway
    -0.81
     Anyway
    -0.77
    channelAvailability
    -0.74
    inho
    -0.74
    DragonMagazine
    -0.71
    unless
    -0.71
    ][/
    -0.71
    âĢ¦)
    -0.70
    ntil
    -0.69
    endif
    -0.69
    POSITIVE LOGITS
     failed
    1.00
     unexpectedly
    0.92
     botched
    0.90
     mistakenly
    0.89
     accidentally
    0.88
     unsuccessful
    0.78
     dared
    0.74
     leaked
    0.74
     deemed
    0.74
     allegedly
    0.73
    Activations Density 0.537%

    No Known Activations