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. 9-RES-JB
    6. 7692
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent acts, particularly massacres and slaughters

    oai_token-act-pair · gpt-3.5-turbo

    references to mass killings or atrocities

    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
    BuyableInstoreAndOnline
    -0.85
    erson
    -0.68
     Benson
    -0.64
    verage
    -0.63
    uve
    -0.62
     Canal
    -0.62
    ibble
    -0.61
    acea
    -0.60
     navig
    -0.59
    iasm
    -0.57
    POSITIVE LOGITS
    quished
    0.96
     slaughtered
    0.95
    houses
    0.92
     massac
    0.91
     Slaughter
    0.91
     Massacre
    0.89
     slaughter
    0.88
     massacre
    0.88
    ocaust
    0.86
     massacres
    0.85
    Activations Density 0.096%

    No Known Activations