© 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. 11-RES-JB
    11. 24152
    Prev
    Next
    INDEX
    Explanations

    phrases related to different sides or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "sides" or perspectives in discussions or arguments

    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
    osponsors
    -0.76
    erion
    -0.72
    imentary
    -0.71
    enza
    -0.71
    obyl
    -0.70
    arious
    -0.69
    obook
    -0.68
    eful
    -0.68
    onial
    -0.66
    reditary
    -0.66
    POSITIVE LOGITS
     things
    1.79
     affairs
    1.59
     events
    1.26
    Things
    1.22
     matters
    1.21
     Things
    1.20
     proceedings
    1.16
    things
    1.04
     everything
    0.99
     life
    0.98
    Activations Density 0.390%

    No Known Activations