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. 5855
    Prev
    Next
    INDEX
    Explanations

    words related to construction or building

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "build" and its variations indicating construction or creation processes

    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
    acting
    -0.69
    soDeliveryDate
    -0.68
    nown
    -0.68
    lah
    -0.66
    ajor
    -0.65
    joy
    -0.64
    icent
    -0.64
     SOS
    -0.64
     MIA
    -0.64
     Humane
    -0.63
    POSITIVE LOGITS
     build
    3.44
     builds
    2.49
     Build
    2.41
    Build
    2.26
    build
    2.21
     rebuild
    1.89
     built
    1.78
     buildup
    1.75
     building
    1.63
    Building
    1.55
    Activations Density 0.026%

    No Known Activations