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. 909
    Prev
    Next
    INDEX
    Explanations

    verbs related to moving or arriving at a destination

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "landed" and its variations, often in the context of arrivals or descents

    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
     Supp
    -0.69
    Reviewer
    -0.69
     Nicotine
    -0.62
    Cla
    -0.60
    esson
    -0.59
     NAD
    -0.59
     Ni
    -0.59
     Bleach
    -0.58
    ablo
    -0.58
     Reloaded
    -0.57
    POSITIVE LOGITS
     landed
    3.55
     landing
    1.91
     lands
    1.70
     land
    1.57
     sailed
    1.50
     Landing
    1.48
     flew
    1.42
     arrived
    1.42
     disembark
    1.38
    Land
    1.32
    Activations Density 0.017%

    No Known Activations