© 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 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. 10-RES-JB
    11. 16571
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicting beliefs or actions within an organization

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to religious teachings and contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     editors
    -0.57
     aback
    -0.55
     analysts
    -0.54
     consolation
    -0.54
     anecd
    -0.54
     wise
    -0.54
     commentators
    -0.53
     strateg
    -0.53
     theolog
    -0.52
     introdu
    -0.52
    POSITIVE LOGITS
    ocaust
    0.75
    pox
    0.67
    illegal
    0.65
    chwitz
    0.65
    ratom
    0.64
    ghazi
    0.63
    azo
    0.61
    usalem
    0.61
    usterity
    0.61
    ihadi
    0.59
    Activations Density 1.409%

    No Known Activations