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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12900
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental departments or ministries related to international or public affairs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government or organizational departments related to affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gling
    -0.92
    ãĤ©
    -0.83
    thumbnails
    -0.74
    emade
    -0.71
    ones
    -0.70
    own
    -0.70
    ilts
    -0.69
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.68
    packed
    -0.67
    ding
    -0.66
    POSITIVE LOGITS
     Affairs
    1.02
     Correspond
    0.89
     Agency
    0.89
     Investigations
    0.84
     Studies
    0.82
     Counsel
    0.82
     Bureau
    0.81
     Consult
    0.79
     Policy
    0.79
     affairs
    0.79
    Activations Density 0.014%

    No Known Activations