© 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. 11-RES-JB
    11. 9506
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal action and investigation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of justice and accountability in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Favorite
    -0.76
    ebus
    -0.73
    artney
    -0.72
    />
    -0.68
     Equip
    -0.67
     Usage
    -0.67
    Theme
    -0.67
    ertility
    -0.66
     presets
    -0.66
     preferences
    -0.65
    POSITIVE LOGITS
     justice
    1.64
     exoner
    1.62
     vind
    1.52
    justice
    1.43
     Prosecut
    1.42
     prosecutions
    1.41
    Justice
    1.40
     prosecution
    1.35
     prosecuting
    1.35
     prosecute
    1.29
    Activations Density 0.843%

    No Known Activations