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. 0-RES-JB
    6. 6997
    Prev
    Next
    INDEX
    Explanations

    mentions of various kinds of "isers" in the context of products, events, and community organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to naval vessels or cruisers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passage
    -0.63
    nec
    -0.60
     Giant
    -0.58
    my
    -0.58
     golden
    -0.55
     Plex
    -0.55
     rug
    -0.55
     detailed
    -0.55
     vault
    -0.54
     Calder
    -0.54
    POSITIVE LOGITS
    isers
    4.46
    izers
    2.97
    iser
    1.78
    izer
    1.58
    isations
    1.43
    ishers
    1.35
    ises
    1.33
     organisers
    1.27
    isation
    1.26
    ising
    1.25
    Activations Density 0.034%

    No Known Activations