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. 4-RES-JB
    6. 18679
    Prev
    Next
    INDEX
    Explanations

    government-related entities and activities, such as local government, authorities, partners, media reporting on government, police force, and government-funded services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and local authorities

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

    No Comments

    Negative Logits
    yss
    -0.74
    idious
    -0.73
     symmetry
    -0.71
     Moonlight
    -0.66
    isy
    -0.66
     Marketable
    -0.63
    ilitarian
    -0.62
    bye
    -0.62
    aundering
    -0.61
     Dull
    -0.60
    POSITIVE LOGITS
     districts
    0.71
    Council
    0.69
    abulary
    0.69
     district
    0.67
    stand
    0.64
     units
    0.63
     District
    0.62
    ////////
    0.62
     tenant
    0.62
    hesion
    0.62
    Activations Density 0.162%

    No Known Activations