© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22230
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of criminal activities and statistical data on crimes such as homicide, theft, and property crimes

    oai_token-act-pair · gpt-3.5-turbo

    statistical references to crime rates and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atari
    -0.79
    soDeliveryDate
    -0.77
    ļéĨĴ
    -0.77
    ëĭ
    -0.75
    hai
    -0.71
     Sparkle
    -0.69
    dit
    -0.68
    Stretch
    -0.68
     sands
    -0.66
    Recipe
    -0.66
    POSITIVE LOGITS
     homicides
    1.98
     homicide
    1.78
     murders
    1.77
     crime
    1.49
     murder
    1.48
     crimes
    1.48
     robberies
    1.47
    crime
    1.46
     killings
    1.44
     shootings
    1.40
    Activations Density 0.471%

    No Known Activations