© 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. 6-RES-JB
    11. 13812
    Prev
    Next
    INDEX
    Explanations

    mentions of arrests and criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    instances of arrest-related events and associated charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tokens
    -0.88
    fried
    -0.77
    TPPStreamerBot
    -0.72
     absorbs
    -0.71
     orphans
    -0.70
    natureconservancy
    -0.68
     absor
    -0.68
     Remastered
    -0.68
    reen
    -0.67
     wip
    -0.64
    POSITIVE LOGITS
     felony
    1.09
     DUI
    1.00
     arra
    0.99
     criminally
    0.97
     DEA
    0.96
     indictment
    0.96
     misdemeanor
    0.92
    eanor
    0.92
    aundering
    0.92
     ATF
    0.91
    Activations Density 0.248%

    No Known Activations