© 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. 9901
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and technological solutions/companies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology solutions and digital services

    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
     canon
    -0.76
    kered
    -0.75
     sidel
    -0.72
     spirited
    -0.71
     "$:/
    -0.71
     marginal
    -0.71
     undes
    -0.70
     stirring
    -0.69
     customary
    -0.69
    -------------
    -0.68
    POSITIVE LOGITS
     Technologies
    1.47
     Solutions
    1.32
     Labs
    1.28
    ®
    1.24
     Networks
    1.19
     Partners
    1.15
     Analytics
    1.15
    ®,
    1.14
    Sense
    1.10
     Ventures
    1.06
    Activations Density 0.408%

    No Known Activations