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. 22879
    Prev
    Next
    INDEX
    Explanations

    names containing the characters "Sha"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sha" in various contexts

    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
     conceive
    -0.69
    orks
    -0.68
     âĨij
    -0.67
    âĨĴ
    -0.65
    GER
    -0.64
    olics
    -0.64
    rants
    -0.64
    olini
    -0.62
     Navigation
    -0.62
    503
    -0.60
    POSITIVE LOGITS
     Sha
    4.01
     Kobe
    1.42
     SHA
    1.33
     Kare
    1.31
     Yao
    1.31
     Shant
    1.31
    sha
    1.30
     Shan
    1.29
    SHA
    1.26
     Sheikh
    1.22
    Activations Density 0.009%

    No Known Activations