© 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. 9-RES-JB
    11. 9862
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of legal charges and possession of controlled substances or weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    town
    -0.81
    isSpecialOrderable
    -0.74
    Phys
    -0.74
    venture
    -0.74
    ventures
    -0.72
    Congress
    -0.71
     pairing
    -0.71
    gradation
    -0.68
    facing
    -0.68
    arth
    -0.68
    POSITIVE LOGITS
     explosives
    1.37
     cocaine
    1.27
     knives
    1.27
     methamphetamine
    1.26
     ammunition
    1.23
     drugs
    1.21
     grenades
    1.18
     weapons
    1.17
     firearms
    1.17
     handguns
    1.14
    Activations Density 0.419%

    No Known Activations