© 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. 7-RES-JB
    11. 2278
    Prev
    Next
    INDEX
    Explanations

    locations associated with tragic events

    oai_token-act-pair · gpt-3.5-turbo

    references to tragic mass shooting events and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requires
    -0.73
    atively
    -0.71
     Celt
    -0.68
    agin
    -0.68
    arial
    -0.67
    Wilson
    -0.67
    alach
    -0.66
    rush
    -0.65
    inav
    -0.63
    onyms
    -0.63
    POSITIVE LOGITS
     Massacre
    0.99
     victims
    0.96
     massacre
    0.95
     fallout
    0.86
     tragedy
    0.85
     shootings
    0.84
    obyl
    0.84
     aftermath
    0.84
     Attacks
    0.83
     carnage
    0.83
    Activations Density 0.174%

    No Known Activations