Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7080
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence and threats

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.86
     Volunte
    -0.81
    aird
    -0.75
    BuyableInstoreAndOnline
    -0.72
     Parables
    -0.71
    assetsadobe
    -0.71
     Quartz
    -0.69
    ĸļ
    -0.68
     Cosponsors
    -0.68
    20439
    -0.68
    POSITIVE LOGITS
     revenge
    0.95
     whoever
    0.93
     retribution
    0.91
     unsuspecting
    0.90
     civilians
    0.89
     havoc
    0.89
     enemies
    0.88
     themselves
    0.86
     enemy
    0.84
     retaliation
    0.82
    Activations Density 0.380%

    No Known Activations