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. 9248
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Cru"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific car models, particularly those associated with the term "Cruiser."

    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
    vernment
    -0.76
     -->
    -0.74
     Mew
    -0.73
    oof
    -0.68
    abled
    -0.67
    elled
    -0.67
    stack
    -0.66
    EMBER
    -0.66
     stack
    -0.66
    dj
    -0.65
    POSITIVE LOGITS
     Cru
    3.49
    cru
    3.45
    Cru
    3.19
     cru
    3.09
     Cruiser
    1.76
     cruiser
    1.74
     Cruise
    1.56
     cruc
    1.33
     cruise
    1.32
     cruising
    1.27
    Activations Density 0.034%

    No Known Activations