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. 3-RES-JB
    6. 11592
    Prev
    Next
    INDEX
    Explanations

    phrases related to tech companies, space exploration, and transportation services

    oai_token-act-pair · gpt-3.5-turbo

    references to SpaceX and, to a lesser extent, Lyft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥĪ
    -0.86
    bred
    -0.78
    venge
    -0.73
    cum
    -0.71
    pron
    -0.71
    ild
    -0.69
    à¨
    -0.68
    phal
    -0.68
     Franks
    -0.67
    igun
    -0.66
    POSITIVE LOGITS
     SpaceX
    0.94
     rockets
    0.78
     rocket
    0.75
     spacecraft
    0.75
     astronauts
    0.74
     Falcon
    0.73
     satellites
    0.73
    heed
    0.73
     leaps
    0.72
     spaceship
    0.71
    Activations Density 0.005%

    No Known Activations