© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    phrases related to indoctrination

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to indoctrination and incrimination

    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
     applause
    -0.72
     Prosecut
    -0.67
     Nare
    -0.67
     Huck
    -0.65
     ACTION
    -0.63
     Duff
    -0.63
     umbrella
    -0.62
     Mellon
    -0.62
     negligence
    -0.62
     Convention
    -0.62
    POSITIVE LOGITS
    ination
    1.18
    inating
    1.18
    ments
    1.03
    metry
    1.02
    inated
    1.00
    inations
    0.99
    yrinth
    0.98
    ming
    0.98
    inatory
    0.97
    plete
    0.95
    Activations Density 0.032%

    No Known Activations