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. 5209
    Prev
    Next
    INDEX
    Explanations

    various phrases related to organization processes and structuring tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or prerequisites for actions

    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
    \":
    -0.67
    ties
    -0.63
     lately
    -0.62
    illon
    -0.62
    theless
    -0.60
    soDeliveryDate
    -0.58
     Patreon
    -0.57
     interviewed
    -0.57
    /#
    -0.55
    */(
    -0.54
    POSITIVE LOGITS
     uninterrupted
    0.75
     freely
    0.75
    ioned
    0.70
     efficiently
    0.70
     seamless
    0.69
     undet
    0.68
    asured
    0.67
     seamlessly
    0.67
     comfortably
    0.66
     cheaply
    0.65
    Activations Density 0.569%

    No Known Activations