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. 9456
    Prev
    Next
    INDEX
    Explanations

    words related to changes, developments, or advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of reality or becoming significant

    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
    76561
    -0.76
    LESS
    -0.69
    PsyNetMessage
    -0.66
     Sons
    -0.65
    é¾įåĸļ士
    -0.65
     Cosponsors
    -0.63
    luaj
    -0.63
     Tours
    -0.63
    who
    -0.63
    axter
    -0.63
    POSITIVE LOGITS
     commonplace
    1.36
     prevalent
    1.22
     viable
    1.18
     norm
    1.12
     fashionable
    1.08
     trendy
    1.06
     predominant
    1.03
     ubiquitous
    1.02
     staple
    1.01
     mainstream
    1.00
    Activations Density 0.309%

    No Known Activations