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. 7-RES-JB
    6. 664
    Prev
    Next
    INDEX
    Explanations

    phrases related to police incidents and emergency response

    oai_token-act-pair · gpt-3.5-turbo

    reports of police activity and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.77
     vetoed
    -0.74
    TPP
    -0.71
     veto
    -0.70
    cair
    -0.70
    PRES
    -0.69
    JP
    -0.69
    imir
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
    anian
    -0.67
    POSITIVE LOGITS
     Detect
    0.89
     Constable
    0.88
     Borough
    0.87
     paramedics
    0.83
     ambul
    0.80
     patrols
    0.78
     probable
    0.76
     Camer
    0.75
     Officers
    0.74
     checkpoints
    0.74
    Activations Density 0.392%

    No Known Activations