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. 11-RES-JB
    6. 20363
    Prev
    Next
    INDEX
    Explanations

    phrases related to official positions, organizations, and government activities

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or official entities and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sucker
    -0.77
     gladly
    -0.70
    sburg
    -0.69
    blank
    -0.68
    podcast
    -0.65
    lees
    -0.64
    sylv
    -0.62
    annah
    -0.62
    åŃIJ
    -0.61
    apy
    -0.61
    POSITIVE LOGITS
     Ministry
    1.33
     Directorate
    1.30
     UNESCO
    1.18
     ministries
    1.08
     Transport
    1.01
     Minister
    1.01
     Tourism
    1.00
     DG
    0.97
     ministry
    0.96
     Planning
    0.95
    Activations Density 0.414%

    No Known Activations