© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 20644
    Prev
    Next
    INDEX
    Explanations

    words related to political systems and power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to forms of governance and political systems

    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
    ãģ¦
    -0.82
    staking
    -0.74
     depot
    -0.70
    listed
    -0.68
    words
    -0.68
    STR
    -0.67
     TRUE
    -0.65
    erman
    -0.65
    wake
    -0.65
    plan
    -0.65
    POSITIVE LOGITS
    acies
    1.23
    ocr
    1.12
    ocratic
    1.03
    ocracy
    0.96
    ocrats
    0.93
    atically
    0.89
    acia
    0.89
    isy
    0.88
    atism
    0.88
    ocrat
    0.87
    Activations Density 0.017%

    No Known Activations