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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10550
    Prev
    Next
    INDEX
    Explanations

    information related to police involvement in various incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement or police-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.87
    opian
    -0.80
    yip
    -0.79
    osi
    -0.76
    pread
    -0.72
    minecraft
    -0.68
    200000
    -0.68
    ocene
    -0.68
    tem
    -0.68
    ãĤ¦
    -0.67
    POSITIVE LOGITS
     officers
    1.20
     departments
    1.12
     officer
    1.09
     Officers
    0.97
     department
    0.96
     commissioner
    0.95
     chiefs
    0.92
     superintendent
    0.91
     chief
    0.87
     headquarters
    0.86
    Activations Density 0.068%

    No Known Activations