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. 9-RES-JB
    6. 6549
    Prev
    Next
    INDEX
    Explanations

    a specific sequence that contains the word "cricke"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'c' across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.74
     Yamaha
    -0.72
     mornings
    -0.64
     contagious
    -0.63
     Maker
    -0.63
     Siberia
    -0.62
     Gors
    -0.62
     bal
    -0.61
     Tycoon
    -0.60
     Lans
    -0.59
    POSITIVE LOGITS
    redits
    1.32
    ategories
    1.28
    ursor
    1.28
    rawl
    1.27
    rossover
    1.27
    rescent
    1.24
    risis
    1.24
    ouple
    1.23
    oding
    1.23
    rowd
    1.22
    Activations Density 0.042%

    No Known Activations