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. 12246
    Prev
    Next
    INDEX
    Explanations

    company names, specifically "Carrier."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company "Carrier" and its associates

    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
     Wiz
    -0.83
    way
    -0.76
     Nir
    -0.75
     Tob
    -0.71
    istry
    -0.69
    :(
    -0.66
     CLS
    -0.66
    ways
    -0.66
    ires
    -0.64
     Gian
    -0.64
    POSITIVE LOGITS
     Carrier
    1.03
    TPPStreamerBot
    0.90
    xon
    0.86
    ategory
    0.85
    quished
    0.84
    mma
    0.83
    thur
    0.81
    esville
    0.81
    cffff
    0.79
    idon
    0.76
    Activations Density 0.031%

    No Known Activations