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. 3171
    Prev
    Next
    INDEX
    Explanations

    Chinese characters as symbols for tattoo designs

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or characters that may indicate a particular type of formatting or encoding in the text

    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
    imen
    -0.78
    icer
    -0.69
    iber
    -0.67
    activation
    -0.67
    eri
    -0.67
    etti
    -0.66
    ulia
    -0.66
    emort
    -0.66
    ners
    -0.65
    ivia
    -0.65
    POSITIVE LOGITS
    è¦
    1.26
    åĮ
    0.71
     Fundamental
    0.68
    Hop
    0.63
     Huck
    0.61
    forts
    0.61
    è¦ļéĨĴ
    0.60
     laure
    0.59
    orph
    0.59
    Tags
    0.58
    Activations Density 0.000%

    No Known Activations