© 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. 4-RES-JB
    11. 16999
    Prev
    Next
    INDEX
    Explanations

    law enforcement agencies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police departments

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

    No Comments

    Negative Logits
    nces
    -0.88
    thumbnails
    -0.83
    opian
    -0.83
    uces
    -0.81
    versions
    -0.80
    xual
    -0.78
    ranged
    -0.77
    igible
    -0.71
    yip
    -0.71
    FACE
    -0.69
    POSITIVE LOGITS
     Commissioner
    1.16
     Officers
    1.11
     Department
    1.10
     Constable
    1.09
     Officer
    1.07
     Enforcement
    1.05
     Accountability
    1.03
     Chief
    1.00
     Dept
    0.98
     Superintendent
    0.97
    Activations Density 0.039%

    No Known Activations