© 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. 9-RES-JB
    11. 7329
    Prev
    Next
    INDEX
    Explanations

    numbers related to the count of people in various scenarios where harm or death is involved

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of people affected by events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.88
    \/\/
    -0.78
    catentry
    -0.74
    inventoryQuantity
    -0.73
    Emer
    -0.64
     Sadd
    -0.63
    Twe
    -0.62
    erenn
    -0.62
     Unleashed
    -0.62
    Corp
    -0.62
    POSITIVE LOGITS
     smugglers
    1.07
    uscript
    0.88
     boarded
    0.87
     attending
    0.84
     who
    0.84
     smuggling
    0.83
     gathered
    0.82
     affected
    0.81
     detained
    0.80
     evacuated
    0.79
    Activations Density 0.092%

    No Known Activations