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. 6-RES-JB
    6. 24142
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology, data privacy, recruitment, newsletter, senior positions, laboratories, mounting hardware, medical conditions, spreads, teams, districts, ex-relationships, new applications, rear positions, yearly reviews, campaigns, geographical locations, cofounders, rights, maps

    oai_token-act-pair · gpt-3.5-turbo

    key terms and important concepts related to organizational activities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.94
    È
    -0.70
    ones
    -0.69
    adish
    -0.69
     Byr
    -0.69
    aples
    -0.68
    pires
    -0.67
     Lank
    -0.66
    ankind
    -0.66
    cair
    -0.65
    POSITIVE LOGITS
     woes
    0.99
     antics
    0.73
     exploits
    0.71
     haul
    0.70
     spree
    0.70
     cz
    0.68
     monopoly
    0.68
     portfolio
    0.67
     takeover
    0.66
     holdings
    0.66
    Activations Density 0.406%

    No Known Activations