© 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. 18666
    Prev
    Next
    INDEX
    Explanations

    mentions of legal entities such as prosecutors and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal authorities and their actions

    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
    oken
    -0.78
    opian
    -0.72
    obyl
    -0.71
    ontent
    -0.70
    PASS
    -0.67
     Revival
    -0.65
    yip
    -0.65
     backward
    -0.64
     Mahar
    -0.64
    eem
    -0.64
    POSITIVE LOGITS
     prosecutor
    0.94
     indicted
    0.91
     prosecuted
    0.89
     allege
    0.89
     prosecutors
    0.86
     subpoen
    0.85
     investigating
    0.84
     prosecuting
    0.82
     proced
    0.81
     investigator
    0.80
    Activations Density 0.030%

    No Known Activations