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. 11-RES-JB
    6. 8751
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "-en"

    oai_token-act-pair · gpt-3.5-turbo

    a variety of proper nouns and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carib
    -0.90
     Boyle
    -0.80
     Bog
    -0.77
     tyr
    -0.77
     Bohem
    -0.75
     Rabbit
    -0.75
     Bolivia
    -0.75
     MGM
    -0.74
     rag
    -0.74
     Cycl
    -0.74
    POSITIVE LOGITS
    en
    1.79
    EN
    1.61
    ename
    1.42
    enf
    1.41
    ens
    1.39
    ena
    1.35
    enh
    1.33
    eni
    1.31
    eng
    1.28
    eny
    1.28
    Activations Density 0.141%

    No Known Activations