Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16582
    Prev
    Next
    INDEX
    Explanations

    names of police officers and law enforcement departments

    oai_token-act-pair · gpt-3.5-turbo

    statements attributed to police officers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intellectuals
    -0.80
    etus
    -0.76
     boycot
    -0.75
     âĤ¬
    -0.74
     neoliberal
    -0.71
    emin
    -0.71
    oliberal
    -0.71
     impover
    -0.68
    Brexit
    -0.67
     boycott
    -0.67
    POSITIVE LOGITS
     COUNTY
    1.07
     Sgt
    1.06
     Officer
    0.99
     Detective
    0.98
    geant
    0.97
    intendent
    0.96
     sheriff
    0.96
     LAPD
    0.94
     troopers
    0.92
     Detect
    0.91
    Activations Density 0.504%

    No Known Activations