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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1096
    Prev
    Next
    INDEX
    Explanations

    phrases related to free market principles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to free market economics and government principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.88
    DoS
    -0.87
    staking
    -0.79
    OUT
    -0.76
    ULAR
    -0.76
    shows
    -0.75
    channelAvailability
    -0.72
    oths
    -0.70
    details
    -0.70
    Bir
    -0.69
    POSITIVE LOGITS
     principles
    1.01
    eers
    0.94
     policies
    0.91
     Initiative
    0.88
     paradise
    0.88
     capitalism
    0.87
     solutions
    0.86
     doctrine
    0.86
     ethos
    0.85
     ideals
    0.85
    Activations Density 0.154%

    No Known Activations