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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 0-RES-JB
    6. 14034
    Prev
    Next
    INDEX
    Explanations

    specific terms related to observation or scrutiny, such as "gaze" and "astronaut"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to focus and vision, particularly in the context of astronauts and their creations

    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
     flushed
    -0.72
    Agg
    -0.67
    ency
    -0.67
    dal
    -0.66
     DU
    -0.66
     Inn
    -0.66
    Rat
    -0.65
    ien
    -0.65
    ENCY
    -0.64
    Deal
    -0.64
    POSITIVE LOGITS
     astronaut
    1.83
     gaze
    1.63
     creations
    1.49
     sculptures
    1.33
     sculpture
    1.19
     spaceship
    1.17
     superhero
    1.14
     spheres
    1.13
     superheroes
    1.08
     sensory
    1.07
    Activations Density 0.031%

    No Known Activations