© 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. 11-RES-JB
    11. 5418
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal permissions and freedoms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rights and freedoms, particularly in the context of living and working conditions

    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
    ãĤ·ãĥ£
    -0.78
    catentry
    -0.77
    mber
    -0.73
    Disk
    -0.66
    ggles
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.63
     Cosponsors
    -0.61
    ciating
    -0.60
    ãĤ©
    -0.60
     aback
    -0.59
    POSITIVE LOGITS
     freely
    1.66
     unrestricted
    1.14
     lawfully
    1.13
     openly
    1.12
     safely
    1.07
     unchecked
    1.06
     anonymously
    1.05
     unim
    1.03
     indefinitely
    0.99
     impunity
    0.99
    Activations Density 0.362%

    No Known Activations