© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17282
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and police actions

    oai_token-act-pair · gpt-3.5-turbo

    references to police officers in various contexts related to their actions and involvement in incidents

    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
     Remastered
    -0.90
    ãĤ¦
    -0.84
    ãĥ¼ãĥĨ
    -0.76
    hered
    -0.74
    hof
    -0.73
    dos
    -0.73
    ãĤ¤ãĥĪ
    -0.73
    âĶģ
    -0.73
    lishing
    -0.72
    åĮ
    -0.72
    POSITIVE LOGITS
     stationed
    1.16
     patrolling
    1.14
     officers
    1.09
     officer
    1.02
    utenant
    1.00
    involved
    0.97
    geant
    0.94
     tasked
    0.92
     misconduct
    0.90
     Officers
    0.88
    Activations Density 0.072%

    No Known Activations