© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 845
    Prev
    Next
    INDEX
    Explanations

    threatening language and violent actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to threats and acts of violence

    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
     Parables
    -0.75
    ACTED
    -0.75
    eret
    -0.74
     Edited
    -0.71
    soDeliveryDate
    -0.68
    :{
    -0.68
    %]
    -0.68
     guiName
    -0.68
     Bought
    -0.66
    Sales
    -0.66
    POSITIVE LOGITS
     retaliation
    1.14
     retribution
    1.08
     repr
    0.96
     eviction
    0.90
     annihilation
    0.83
     endanger
    0.81
     threats
    0.80
     retaliate
    0.80
     perman
    0.80
     retali
    0.79
    Activations Density 0.142%

    No Known Activations