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. 12-RES-JB
    6. 14521
    Prev
    Next
    INDEX
    Explanations

    information related to crime statistics, police behavior, and social justice issues particularly regarding racial profiling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    themes related to racial profiling and policing practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    oslov
    -0.81
    ilateral
    -0.79
    apult
    -0.70
     UNESCO
    -0.70
     Producer
    -0.68
    nuclear
    -0.68
    ogun
    -0.68
    æĪ¦
    -0.68
    ovation
    -0.68
    atorial
    -0.67
    POSITIVE LOGITS
     robberies
    1.47
     arrests
    1.21
     burgl
    1.19
     juveniles
    1.18
     suspects
    1.18
     homicides
    1.18
     shootings
    1.15
     patrols
    1.15
     crimes
    1.13
     warrants
    1.12
    Activations Density 0.541%

    No Known Activations