© 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. 3-RES-JB
    11. 17777
    Prev
    Next
    INDEX
    Explanations

    phrases related to civil liberties and rights

    oai_token-act-pair · gpt-3.5-turbo

    references to civil liberties and freedoms

    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
    HEAD
    -0.73
    olls
    -0.62
     Reincarn
    -0.62
    Hyper
    -0.61
    orah
    -0.60
    PM
    -0.59
    ded
    -0.59
    amed
    -0.58
    otte
    -0.57
    ptive
    -0.57
    POSITIVE LOGITS
     liberties
    1.19
     Liberties
    1.15
     freedoms
    1.12
     rights
    0.92
     Rights
    0.90
     protections
    0.90
    ktop
    0.88
     liberty
    0.82
    tarians
    0.82
    acies
    0.81
    Activations Density 0.006%

    No Known Activations