© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    phrases related to aggressive actions or criticisms directed towards something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to aggressive confrontations and disputes

    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
    artifacts
    -0.74
    OTA
    -0.71
    ylan
    -0.68
     Wonders
    -0.68
     Suc
    -0.66
    soDeliveryDate
    -0.66
    hess
    -0.65
    scope
    -0.65
     orderly
    -0.63
    sterdam
    -0.63
    POSITIVE LOGITS
     accusing
    1.20
     insults
    1.08
     slurs
    1.06
     leveled
    1.03
     slander
    1.03
     tir
    1.00
     denouncing
    0.99
     criticizing
    0.98
     accusation
    0.97
     dispar
    0.97
    Activations Density 0.249%

    No Known Activations