© 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. 8-RES-JB
    11. 1766
    Prev
    Next
    INDEX
    Explanations

    Latin characters that signal the start of a section in an article

    oai_token-act-pair · gpt-3.5-turbo

    topics related to legal issues or societal controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.78
    ignty
    -0.74
     persuasion
    -0.71
     excel
    -0.69
     emperor
    -0.69
     reneg
    -0.68
     regener
    -0.67
     smoot
    -0.67
     detract
    -0.67
     deterior
    -0.67
    POSITIVE LOGITS
    According
    1.41
    Interested
    1.38
    Sources
    1.34
    Writing
    1.24
    The
    1.24
    Specifically
    1.21
    Speaking
    1.19
    Following
    1.19
    Instead
    1.18
    While
    1.17
    Activations Density 0.253%

    No Known Activations