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. 19752
    Prev
    Next
    INDEX
    Explanations

    phrases and proper nouns related to the person "Müller"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with the term "uer."

    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
     performing
    -0.69
     loading
    -0.68
     hacking
    -0.63
     mounted
    -0.63
     fields
    -0.62
     intercept
    -0.61
     hop
    -0.61
     marathon
    -0.60
     electrical
    -0.58
     Internet
    -0.58
    POSITIVE LOGITS
    uer
    4.81
    uers
    2.75
    ued
    1.72
    ues
    1.69
    uing
    1.66
    ue
    1.44
    urer
    1.32
    UE
    1.32
    uel
    1.29
    uder
    1.15
    Activations Density 0.011%

    No Known Activations