© 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. 10-RES-JB
    11. 10039
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or formal actions and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adden
    -0.76
     neocons
    -0.76
     nonpartisan
    -0.76
     matchups
    -0.75
     aligned
    -0.74
     NAFTA
    -0.73
     foundational
    -0.71
    BILL
    -0.71
     matchup
    -0.70
     breadth
    -0.70
    POSITIVE LOGITS
    Luckily
    1.16
     apologised
    1.04
    Thankfully
    1.04
    Fortunately
    0.99
     luckily
    0.97
     apologise
    0.96
    Hopefully
    0.94
     Luckily
    0.93
     Thankfully
    0.92
     organisers
    0.88
    Activations Density 0.679%

    No Known Activations