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. 11-RES-JB
    6. 18890
    Prev
    Next
    INDEX
    Explanations

    terms related to physical actions, possibly violent or forceful

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical injury or trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scholarship
    -0.91
     diversity
    -0.89
     sponsorship
    -0.87
     Diversity
    -0.84
     promotion
    -0.81
     demographics
    -0.80
     education
    -0.79
     partnership
    -0.79
     Mobil
    -0.78
     democracy
    -0.77
    POSITIVE LOGITS
    dro
    1.15
    gently
    1.06
    crow
    1.03
    eyes
    1.03
    near
    1.02
    sharp
    1.01
    inside
    1.01
    empty
    1.00
    then
    1.00
    feet
    0.99
    Activations Density 0.284%

    No Known Activations