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. 10-RES-JB
    6. 23143
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription services

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude towards the reader or subscriber

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haas
    -0.65
     displ
    -0.61
     "...
    -0.61
     Paddock
    -0.60
    ignty
    -0.59
     mos
    -0.57
     Vengeance
    -0.57
     euth
    -0.55
     delinqu
    -0.54
    ership
    -0.54
    POSITIVE LOGITS
    ा
    0.77
    ITAL
    0.68
    à¥
    0.65
    yg
    0.65
    LOCK
    0.64
    âĿ
    0.63
    quished
    0.63
     subscribing
    0.63
    é¾į
    0.62
    à¤
    0.62
    Activations Density 0.013%

    No Known Activations