© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17364
    Prev
    Next
    INDEX
    Explanations

    references to events or conferences, particularly related to technology and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to specific conventions and expos related to games and technology

    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
     uninsured
    -0.68
    uyomi
    -0.67
    oan
    -0.63
    pie
    -0.62
    hearted
    -0.61
     bom
    -0.60
    bats
    -0.60
     composing
    -0.59
    interest
    -0.59
    ictionary
    -0.58
    POSITIVE LOGITS
     attendees
    1.27
    ivals
    1.21
     Expo
    1.18
     keynote
    1.16
     2015
    1.04
     2017
    1.03
     festivities
    1.03
     2014
    1.01
    2015
    0.99
    2018
    0.98
    Activations Density 0.222%

    No Known Activations