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. 10552
    Prev
    Next
    INDEX
    Explanations

    words related to the field of aviation

    oai_token-act-pair · gpt-3.5-turbo

    references to aviation and its related concepts

    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
     Priest
    -0.76
    locks
    -0.70
    weak
    -0.68
    -----------
    -0.68
     slur
    -0.65
    >>\
    -0.65
     Myster
    -0.65
     Fiona
    -0.64
    hook
    -0.63
     taunt
    -0.63
    POSITIVE LOGITS
     Aviation
    3.59
     aviation
    3.48
     aerospace
    2.00
     Aircraft
    1.94
     Aerospace
    1.84
     aircraft
    1.70
     airlines
    1.61
    ircraft
    1.56
     airline
    1.56
     airliner
    1.55
    Activations Density 0.017%

    No Known Activations