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. 19785
    Prev
    Next
    INDEX
    Explanations

    references or mentions of a specific character or entity named "Pop"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Pop."

    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
    %%%%
    -0.76
    åŃIJ
    -0.75
    terday
    -0.74
    Ø©
    -0.74
    Downloadha
    -0.71
    BILITIES
    -0.70
     livest
    -0.70
    RAW
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.68
    ||||
    -0.67
    POSITIVE LOGITS
    ulations
    1.26
    corn
    1.22
    ulated
    1.08
    ulus
    1.07
    ulate
    1.03
    ulates
    1.01
    uli
    0.99
    ulating
    0.98
    ularity
    0.96
    ulation
    0.94
    Activations Density 0.008%

    No Known Activations