Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19372
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents involving shootings

    oai_token-act-pair · gpt-3.5-turbo

    references to mass shootings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amina
    -0.78
    NAS
    -0.67
    atom
    -0.66
    BuyableInstoreAndOnline
    -0.65
    obo
    -0.65
    hr
    -0.63
    croft
    -0.63
    orph
    -0.62
    bid
    -0.62
    gres
    -0.62
    POSITIVE LOGITS
     shootings
    1.25
     spree
    1.16
     shooting
    0.93
    aurus
    0.87
     shooters
    0.86
    eers
    0.85
     rampage
    0.83
     Shooting
    0.82
    nikov
    0.80
    quished
    0.79
    Activations Density 0.009%

    No Known Activations