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. 7-RES-JB
    6. 16260
    Prev
    Next
    INDEX
    Explanations

    mentions of tragic events or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to tragic events or circumstances

    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
    paio
    -0.78
    ebus
    -0.77
    indal
    -0.77
    idable
    -0.71
    llular
    -0.71
    gars
    -0.71
     toilets
    -0.69
     irrig
    -0.69
    cellent
    -0.69
    ership
    -0.69
    POSITIVE LOGITS
     tragic
    0.97
     tragedies
    0.93
    omic
    0.92
    omas
    0.89
     tragedy
    0.87
     Deaths
    0.86
     deaths
    0.86
     victim
    0.85
     bystand
    0.82
     tale
    0.79
    Activations Density 0.039%

    No Known Activations