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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14937
    Prev
    Next
    INDEX
    Explanations

    phrases related to making an argument or point

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases related to beliefs and opinions

    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
    araoh
    -0.64
    youtube
    -0.62
     unsuspecting
    -0.62
    FOX
    -0.61
    Hundreds
    -0.60
    someone
    -0.60
    Thank
    -0.60
    Thousands
    -0.58
    iuses
    -0.58
    SPONSORED
    -0.58
    POSITIVE LOGITS
     differentiation
    0.86
     specificity
    0.79
     heterogeneity
    0.79
     consistency
    0.75
     differences
    0.75
     breadth
    0.73
     continuity
    0.73
     emphasis
    0.72
     attrition
    0.71
     durability
    0.71
    Activations Density 0.913%

    No Known Activations