© 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. 6861
    Prev
    Next
    INDEX
    Explanations

    phrases related to foundational beliefs or moral principles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to foundational ideals and principles

    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
    zed
    -0.74
    Poké
    -0.72
    illion
    -0.68
    kees
    -0.68
    reau
    -0.67
    lets
    -0.67
    blow
    -0.66
    SPONSORED
    -0.65
    rance
    -0.65
    ģ«
    -0.64
    POSITIVE LOGITS
     premise
    1.28
     notion
    1.26
     assumption
    1.16
     laure
    1.15
     principles
    1.07
     belief
    1.06
     principle
    1.06
     idea
    1.03
     ideals
    1.00
     tenets
    0.98
    Activations Density 0.484%

    No Known Activations