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. 6-RES-JB
    6. 3509
    Prev
    Next
    INDEX
    Explanations

    statistics or facts about large groups of people, particularly in a global context

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of people affected by various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.78
     Monkey
    -0.69
    SourceFile
    -0.69
     Dispatch
    -0.66
     Ratt
    -0.65
     Handler
    -0.63
     Franch
    -0.63
     Inquis
    -0.62
     Silence
    -0.61
     Courier
    -0.60
    POSITIVE LOGITS
     worldwide
    1.11
     nationwide
    0.93
     annually
    0.89
     crammed
    0.89
     surveyed
    0.80
     apiece
    0.79
     marched
    0.79
     polled
    0.76
    illion
    0.76
     globally
    0.76
    Activations Density 0.185%

    No Known Activations