© 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. 7-RES-JB
    11. 21196
    Prev
    Next
    INDEX
    Explanations

    terms related to destruction, damage, and negative impacts

    oai_token-act-pair · gpt-3.5-turbo

    references to the destruction of property or civilizations

    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
    soDeliveryDate
    -0.73
    udic
    -0.73
    eus
    -0.71
    pport
    -0.69
    swer
    -0.69
    Magikarp
    -0.69
    eeks
    -0.67
     approving
    -0.67
    orney
    -0.66
    REDACTED
    -0.66
    POSITIVE LOGITS
     havoc
    0.97
     habitat
    0.87
     limb
    0.84
     foundations
    0.84
     windshield
    0.84
     seams
    0.83
     entire
    0.83
     infrastructure
    0.81
     Leviathan
    0.80
     kidneys
    0.80
    Activations Density 0.312%

    No Known Activations