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. 24424
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the concept of money and wealth, specifically in relation to pockets

    oai_token-act-pair · gpt-3.5-turbo

    references to financial concepts and the idea of physical metaphorical "pockets."

    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
     ANGEL
    -0.91
    SHIP
    -0.70
     Abuse
    -0.69
    DE
    -0.68
    ctive
    -0.67
    actionDate
    -0.65
    ãģķ
    -0.64
    GA
    -0.63
    DEF
    -0.63
    rd
    -0.62
    POSITIVE LOGITS
     pockets
    1.26
     pocket
    1.19
    pocket
    1.15
     pouch
    0.89
     lining
    0.85
    ython
    0.82
    aucuses
    0.82
    pots
    0.78
    ensibly
    0.77
     overflowing
    0.77
    Activations Density 0.007%

    No Known Activations