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. 5-RES-JB
    6. 14601
    Prev
    Next
    INDEX
    Explanations

    phrases related to spinning or rotation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spinning" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.79
    76561
    -0.76
    éĹĺ
    -0.71
    bour
    -0.71
    orers
    -0.70
    artment
    -0.70
    put
    -0.69
    ãģ®å
    -0.67
    eq
    -0.67
    irez
    -0.66
    POSITIVE LOGITS
    irling
    0.98
     spinning
    0.97
     weaving
    0.88
     spins
    0.86
     slic
    0.84
    tails
    0.83
     vortex
    0.83
    ernaut
    0.82
     spun
    0.80
    lass
    0.80
    Activations Density 0.045%

    No Known Activations