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. 14007
    Prev
    Next
    INDEX
    Explanations

    words related to sensory experiences, particularly scents and sounds

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" with varying frequencies, indicating a focus on possession or association

    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
    orthy
    -0.87
    imens
    -0.80
    igun
    -0.78
    ials
    -0.70
    ESA
    -0.70
    employ
    -0.69
    wcs
    -0.69
    VP
    -0.68
    OPLE
    -0.68
    ISC
    -0.67
    POSITIVE LOGITS
     darkness
    0.82
     Darkness
    0.75
     heaven
    0.74
     Nanto
    0.73
     truth
    0.72
     light
    0.71
     sunlight
    0.68
     unbeliev
    0.68
     desperation
    0.68
     doom
    0.67
    Activations Density 0.242%

    No Known Activations