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. 10-RES-JB
    6. 369
    Prev
    Next
    INDEX
    Explanations

    instances where there is emphasis on the importance of knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of knowledge and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.70
    interstitial
    -0.70
    ŃĶ
    -0.68
    phrine
    -0.67
    uries
    -0.67
    twitch
    -0.64
    onding
    -0.63
     entreprene
    -0.62
     exting
    -0.61
    avored
    -0.60
    POSITIVE LOGITS
     how
    1.15
    ledge
    1.14
     beforehand
    1.13
     about
    1.10
     exactly
    1.07
     why
    1.02
     WHY
    1.01
     ABOUT
    0.99
     whats
    0.99
    lege
    0.98
    Activations Density 0.072%

    No Known Activations