© 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. 1-RES-JB
    11. 20120
    Prev
    Next
    INDEX
    Explanations

    news articles related to incidents involving authorities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authoritative entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breath
    -0.69
     immersion
    -0.68
     direction
    -0.67
    stood
    -0.66
     towel
    -0.64
     fluid
    -0.64
     patience
    -0.62
     maxim
    -0.60
     nominal
    -0.59
     bearings
    -0.59
    POSITIVE LOGITS
    chwitz
    0.87
    Authorities
    0.84
     Officials
    0.83
    Police
    0.81
    agascar
    0.78
     Authorities
    0.76
     Constable
    0.74
    Officials
    0.73
     Investigators
    0.73
    ashtra
    0.73
    Activations Density 0.052%

    No Known Activations