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. 9-RES-JB
    6. 122
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects being turned upside down

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "upside down" and related concepts of opportunity or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocally
    -0.85
    è¦ļéĨĴ
    -0.79
    imens
    -0.75
    naire
    -0.75
    iston
    -0.74
    assetsadobe
    -0.69
    Nation
    -0.69
    ivity
    -0.68
    alde
    -0.67
    éļ
    -0.67
    POSITIVE LOGITS
     upside
    0.88
    verted
    0.81
    ward
    0.79
     down
    0.79
    zzle
    0.75
     downwards
    0.71
    ï¸
    0.70
     heel
    0.70
    vable
    0.67
    side
    0.67
    Activations Density 0.055%

    No Known Activations