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. 10-RES-JB
    6. 9135
    Prev
    Next
    INDEX
    Explanations

    phrases related to aircraft incidents

    oai_token-act-pair · gpt-3.5-turbo

    incidents or events involving aircraft being shot down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    galitarian
    -0.72
     Homeless
    -0.72
     Xander
    -0.70
     Hyde
    -0.69
    Kings
    -0.69
     eviction
    -0.68
     Patreon
    -0.68
     sts
    -0.68
     cultivate
    -0.68
     Juven
    -0.67
    POSITIVE LOGITS
     airliner
    1.54
     MH
    1.39
     wreckage
    1.35
     Malaysian
    1.27
     Malaysia
    1.23
    selage
    1.23
     Flight
    1.23
     Boeing
    1.22
     aircraft
    1.20
     crashed
    1.15
    Activations Density 0.164%

    No Known Activations