Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10708
    Prev
    Next
    INDEX
    Explanations

    phrases related to aviation incidents and specific flight numbers, in particular referencing Malaysia Airlines Flight MH370

    oai_token-act-pair · gpt-3.5-turbo

    references to specific flight numbers and incidents related to aviation events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦
    -0.86
    ãĥ¼ãĥĨ
    -0.81
    vier
    -0.74
    cess
    -0.74
    ãĤ½
    -0.71
    alties
    -0.71
    cer
    -0.69
    ptroller
    -0.69
    ////////
    -0.68
    ãĥ´ãĤ¡
    -0.67
    POSITIVE LOGITS
     Lumpur
    1.15
     airliner
    0.97
    370
    0.96
    oney
    0.93
     MH
    0.83
    rals
    0.77
    allery
    0.74
    uling
    0.72
    MH
    0.69
    awk
    0.69
    Activations Density 0.013%

    No Known Activations