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. 1-RES-JB
    6. 17518
    Prev
    Next
    INDEX
    Explanations

    references to the term "Kid"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Kid" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prevailing
    -0.76
     brunt
    -0.73
     contractor
    -0.70
    ylon
    -0.70
     confir
    -0.70
    anwhile
    -0.70
     heaviest
    -0.69
     commission
    -0.69
     ministers
    -0.68
     contractors
    -0.67
    POSITIVE LOGITS
    neys
    1.17
    Kid
    1.15
    ney
    1.09
     Icar
    1.04
    kid
    1.03
     Kid
    0.96
    amac
    0.93
    alos
    0.88
     Tut
    0.82
    bean
    0.82
    Activations Density 0.006%

    No Known Activations