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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 14593
    Prev
    Next
    INDEX
    Explanations

    words related to aviation or landings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'landing'

    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
    MpServer
    -0.76
    idia
    -0.67
     Hearts
    -0.67
     Nicotine
    -0.66
    inness
    -0.63
    NRS
    -0.63
     Anonymous
    -0.63
     Mahjong
    -0.61
     Orwell
    -0.61
    soType
    -0.60
    POSITIVE LOGITS
     landing
    3.86
     Landing
    2.66
     landed
    1.83
     takeoff
    1.62
     landfall
    1.38
     land
    1.33
     parachute
    1.25
     lands
    1.24
     docking
    1.23
     disembark
    1.19
    Activations Density 0.006%

    No Known Activations