© 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. 7-RES-JB
    11. 22851
    Prev
    Next
    INDEX
    Explanations

    statistical information on various types of crimes and accidents

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to accidents, crimes, and deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -1.03
    odox
    -0.89
    arity
    -0.87
    ebus
    -0.86
    çīĪ
    -0.81
    dit
    -0.76
    gemony
    -0.72
    IRT
    -0.71
     principle
    -0.68
    IONS
    -0.68
    POSITIVE LOGITS
     homicides
    1.05
    icides
    0.90
     fatalities
    0.88
     suicides
    0.86
     offenses
    0.85
     deaths
    0.85
     per
    0.82
     homicide
    0.82
     attributable
    0.80
     DV
    0.79
    Activations Density 0.353%

    No Known Activations