© 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. 0-RES-JB
    11. 2856
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement officers and their actions

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement officers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bracket
    -0.66
     hosts
    -0.65
     flu
    -0.63
    ahead
    -0.61
     decon
    -0.61
     flock
    -0.60
     comprehens
    -0.60
    ascus
    -0.58
    ait
    -0.58
    versions
    -0.58
    POSITIVE LOGITS
     Officer
    3.88
     Officers
    2.68
    Offic
    2.24
     officer
    2.18
     Sergeant
    1.81
    Officers
    1.79
     Trooper
    1.74
     Sgt
    1.73
     Detective
    1.67
     officers
    1.65
    Activations Density 0.012%

    No Known Activations