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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 9190
    Prev
    Next
    INDEX
    Explanations

    descriptions of criminal events and pursuits

    oai_token-act-pair · gpt-3.5-turbo

    events related to criminal activities and police encounters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.73
     imbalance
    -0.67
     inoc
    -0.67
    umbnail
    -0.62
    reciation
    -0.62
    olars
    -0.61
     embry
    -0.61
     OLED
    -0.61
     bestowed
    -0.61
     honoured
    -0.61
    POSITIVE LOGITS
     chase
    1.07
     police
    1.02
     parked
    1.01
    police
    0.99
     pursued
    0.97
     gunfire
    0.97
    APD
    0.97
     chased
    0.96
    Police
    0.96
     fleeing
    0.93
    Activations Density 0.300%

    No Known Activations