© 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. 6-RES-JB
    11. 11856
    Prev
    Next
    INDEX
    Explanations

    numerical mentions of the quantity of people involved in incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of casualties or fatalities related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.83
    inventoryQuantity
    -0.79
    Corp
    -0.76
    SPONSORED
    -0.76
    catentry
    -0.72
    ebook
    -0.71
    Emer
    -0.70
     Lank
    -0.67
     Sadd
    -0.67
     Parables
    -0.66
    POSITIVE LOGITS
     smugglers
    0.99
    ava
    0.83
     perished
    0.81
     who
    0.81
     affected
    0.80
     attending
    0.79
     fleeing
    0.79
     evacuated
    0.79
     detained
    0.79
     gathered
    0.78
    Activations Density 0.078%

    No Known Activations