© 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. 9-RES-JB
    11. 11399
    Prev
    Next
    INDEX
    Explanations

    references to tragic events, particularly the Sandy Hook Elementary School shooting in Newtown

    oai_token-act-pair · gpt-3.5-turbo

    references to tragic events and locations associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dub
    -0.67
    urally
    -0.66
    ophy
    -0.65
    rist
    -0.64
    cham
    -0.62
    atively
    -0.62
     Celt
    -0.61
    coe
    -0.61
    llan
    -0.61
    cut
    -0.60
    POSITIVE LOGITS
     victims
    0.97
     aftermath
    0.92
     Massacre
    0.91
     fallout
    0.86
     Victims
    0.84
     massacre
    0.81
    quished
    0.77
     survivor
    0.77
    anooga
    0.76
     tragedy
    0.74
    Activations Density 0.142%

    No Known Activations