© 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. 12314
    Prev
    Next
    INDEX
    Explanations

    references to legal rights and constitutional rights

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individual rights and constitutional protections

    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
    DAQ
    -0.93
    coni
    -0.71
    arette
    -0.69
    aco
    -0.65
    cit
    -0.64
    ature
    -0.64
    hiba
    -0.64
    arettes
    -0.63
     Remastered
    -0.61
     srfAttach
    -0.61
    POSITIVE LOGITS
    eous
    0.99
     wing
    0.84
    wing
    0.81
     conferred
    0.79
    rights
    0.73
    move
    0.71
     fielder
    0.69
     rights
    0.69
     winger
    0.68
    mares
    0.66
    Activations Density 0.042%

    No Known Activations