Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20120
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    references to social injustice and systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Got
    -0.85
     Anyway
    -0.82
    IFIED
    -0.80
     Rasm
    -0.75
    Anyway
    -0.75
    Awesome
    -0.74
    kids
    -0.70
     Jurassic
    -0.70
    Gall
    -0.69
    running
    -0.67
    POSITIVE LOGITS
     strive
    1.55
     seek
    1.40
     emphasize
    1.37
     cultivate
    1.35
     endeavor
    1.29
     prioritize
    1.28
     esche
    1.24
     embody
    1.22
     empower
    1.19
     foster
    1.18
    Activations Density 0.384%

    No Known Activations