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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4061
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and policing

    oai_token-act-pair · gpt-3.5-turbo

    references to policing and its various associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ija
    -0.81
    sa
    -0.72
    deal
    -0.70
    elta
    -0.69
    bia
    -0.69
    eria
    -0.69
    sighted
    -0.68
    ifi
    -0.67
    jri
    -0.66
    endant
    -0.66
    POSITIVE LOGITS
    eering
    0.90
    pherd
    0.72
    OPLE
    0.71
    tons
    0.68
    GGGGGGGG
    0.68
    HAM
    0.67
    âĸ¬âĸ¬
    0.66
    âĸ¬
    0.65
     spree
    0.64
     ado
    0.64
    Activations Density 0.041%

    No Known Activations