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. 2-RES-JB
    6. 18040
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Cantonese."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Cant" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.78
    Reviewer
    -0.77
    POSE
    -0.70
    HEAD
    -0.66
    heads
    -0.66
    issance
    -0.66
    vironment
    -0.65
    CVE
    -0.65
    vernment
    -0.65
    */(
    -0.65
    POSITIVE LOGITS
    illon
    0.99
     Cant
    0.97
    onso
    0.86
    rell
    0.82
    alon
    0.78
    aleb
    0.78
    een
    0.78
    esian
    0.77
    rip
    0.75
    asia
    0.74
    Activations Density 0.004%

    No Known Activations