© 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. 0-RES-JB
    11. 6154
    Prev
    Next
    INDEX
    Explanations

    words related to violence and killing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to killing or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ref
    -0.66
     embodiment
    -0.63
     embodiments
    -0.62
     dim
    -0.62
     fib
    -0.62
     candid
    -0.61
     visibly
    -0.61
     aged
    -0.61
     infl
    -0.60
     cent
    -0.60
    POSITIVE LOGITS
    kill
    4.67
    Kill
    2.10
    killed
    1.92
    killing
    1.78
     Kill
    1.35
    shoot
    1.28
     Killing
    1.27
     kill
    1.24
    killers
    1.24
    death
    1.19
    Activations Density 0.006%

    No Known Activations