© 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 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. 8-RES-JB
    11. 1026
    Prev
    Next
    INDEX
    Explanations

    information about casualties or injuries in news reports

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating casualties or injuries in a context related to events or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.89
    #$
    -0.76
    sonian
    -0.74
    Nothing
    -0.74
    feeding
    -0.71
     Unless
    -0.69
     Nope
    -0.67
     ¯
    -0.67
     Dragonbound
    -0.66
     Druid
    -0.65
    POSITIVE LOGITS
     crammed
    1.05
     hospitalized
    0.91
     gathered
    0.91
    athi
    0.87
     killed
    0.87
     unaccount
    0.87
     evacuated
    0.85
     injured
    0.83
     surveyed
    0.83
     detained
    0.82
    Activations Density 0.169%

    No Known Activations