© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12725
    Prev
    Next
    INDEX
    Explanations

    words related to legal issues and crimes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to serious crimes and legal issues

    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
    izons
    -1.07
    natureconservancy
    -0.83
     centr
    -0.78
     balanced
    -0.77
     lofty
    -0.76
     unified
    -0.75
     equilibrium
    -0.75
     univers
    -0.75
     brighter
    -0.73
     gears
    -0.73
    POSITIVE LOGITS
     theft
    1.35
     thefts
    1.27
     robbery
    1.25
     offences
    1.24
     kidnapping
    1.24
     crimes
    1.23
    angering
    1.21
    criminal
    1.21
     robberies
    1.20
    illegal
    1.19
    Activations Density 0.362%

    No Known Activations