© 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. 0-RES-JB
    11. 14858
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.83
     marqu
    -0.70
     Ret
    -0.65
     Volt
    -0.62
     curses
    -0.61
     envy
    -0.60
    efer
    -0.60
     Metatron
    -0.59
     masturb
    -0.59
     caric
    -0.58
    POSITIVE LOGITS
    SO
    4.07
     SO
    2.66
    so
    1.15
    CO
    1.05
    PO
    1.01
    NO
    1.00
     SOM
    0.99
     SOC
    0.96
    GO
    0.93
     SOL
    0.91
    Activations Density 0.022%

    No Known Activations