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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16879
    Prev
    Next
    INDEX
    Explanations

    reports of violent events resulting in multiple casualties

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to death and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -1.01
    atum
    -0.75
    isphere
    -0.73
    soType
    -0.69
    chart
    -0.69
    ater
    -0.68
    arity
    -0.67
     athlet
    -0.67
    aters
    -0.67
    anwhile
    -0.67
    POSITIVE LOGITS
     civilians
    0.99
     spree
    0.96
     him
    0.86
     innocent
    0.80
     dozens
    0.79
     rampage
    0.78
     somebody
    0.78
     terrorists
    0.78
     Osama
    0.75
     lots
    0.75
    Activations Density 0.060%

    No Known Activations