© 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. 9-RES-JB
    11. 6931
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions resulting in death

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing violent deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    -0.71
     Known
    -0.62
     Volunteers
    -0.61
     Swordsman
    -0.59
    eller
    -0.58
    Cola
    -0.58
     Observer
    -0.58
     Returning
    -0.56
    holder
    -0.56
     WATCHED
    -0.55
    POSITIVE LOGITS
     death
    1.16
    wered
    0.94
     shred
    0.88
    death
    0.87
     perfection
    0.84
     pieces
    0.81
     extinction
    0.79
     pulp
    0.75
    asted
    0.74
    otin
    0.74
    Activations Density 0.163%

    No Known Activations