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. 8-RES-JB
    6. 21675
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of continuing or persistence is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continue" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aster
    -0.75
    arta
    -0.74
    oster
    -0.73
    istani
    -0.72
    ologue
    -0.71
    ard
    -0.71
    */(
    -0.70
    MpServer
    -0.69
    dylib
    -0.68
    arse
    -0.67
    POSITIVE LOGITS
     uninterrupted
    0.87
     unab
    0.82
     progressing
    0.78
     indefinitely
    0.75
     experimenting
    0.71
     onward
    0.71
     hostilities
    0.70
     vigil
    0.68
     ap
    0.67
     exploring
    0.67
    Activations Density 0.062%

    No Known Activations