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. 11-RES-JB
    6. 19343
    Prev
    Next
    INDEX
    Explanations

    instances of police activity and crime events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of police-related events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     crore
    -0.88
    Tomorrow
    -0.86
    Ranked
    -0.81
    TPP
    -0.80
    Congratulations
    -0.80
    yright
    -0.79
    inav
    -0.78
    soDeliveryDate
    -0.74
    Personally
    -0.73
     Personally
    -0.73
    POSITIVE LOGITS
     officers
    1.55
     deputies
    1.51
     paramedics
    1.49
     troopers
    1.41
     police
    1.40
     cops
    1.37
     bystanders
    1.35
     detectives
    1.34
     investigators
    1.34
     Officer
    1.29
    Activations Density 0.307%

    No Known Activations