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. 21802
    Prev
    Next
    INDEX
    Explanations

    documents discussing legal activities, such as court cases, reports, and investigations

    oai_token-act-pair · gpt-3.5-turbo

    patterns of reporting or claims made about events and actions involving organizations and interactions

    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
     loves
    -0.68
     sleeps
    -0.67
     nic
    -0.66
     Lov
    -0.66
     Tycoon
    -0.66
     AMA
    -0.64
     mastering
    -0.64
     Sly
    -0.62
     Nurs
    -0.62
     ãģ
    -0.61
    POSITIVE LOGITS
     abound
    1.02
     circulated
    0.82
    senal
    0.81
     aired
    0.80
    qqa
    0.79
    confirmed
    0.79
     prolifer
    0.78
     unanswered
    0.76
    avering
    0.76
    issued
    0.75
    Activations Density 0.402%

    No Known Activations