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. 3-RES-JB
    6. 11140
    Prev
    Next
    INDEX
    Explanations

    words related to the brand "Rover"

    oai_token-act-pair · gpt-3.5-turbo

    the word "blume" or variations of it, indicating a focus on a specific theme or topic related to "blume."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.58
    Mini
    -0.57
     plank
    -0.57
    fram
    -0.56
    nell
    -0.56
    ansom
    -0.56
    obal
    -0.55
     sorely
    -0.55
    talk
    -0.54
    oled
    -0.54
    POSITIVE LOGITS
    ume
    1.06
    umes
    1.05
    uming
    0.90
    OPLE
    0.90
    udi
    0.86
    asus
    0.85
    ose
    0.83
    ury
    0.76
    bane
    0.74
    UME
    0.74
    Activations Density 0.016%

    No Known Activations