© 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. 12-RES-JB
    11. 3622
    Prev
    Next
    INDEX
    Explanations

    phrases related to law, responsibility, and ethics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements about accountability and ethical conduct in governance and law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    NetMessage
    -1.13
    senal
    -0.95
    Els
    -0.87
    moil
    -0.86
    gebra
    -0.83
    osponsors
    -0.81
    rongh
    -0.79
    ËĪ
    -0.78
     Reloaded
    -0.78
     teasp
    -0.78
    POSITIVE LOGITS
     impartial
    1.31
     faithfully
    1.24
     impart
    1.13
     lawfully
    1.12
     appropriately
    1.10
     prudent
    1.10
     unbiased
    1.09
     fairness
    1.09
     lawful
    1.08
     duly
    1.08
    Activations Density 0.432%

    No Known Activations