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

    Neuronpedia

    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. 4880
    Prev
    Next
    INDEX
    Explanations

    writing elements indicating the author's opinion or point of view

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating ownership of opinions and the distinction between personal views and those of larger entities or groups

    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
    isite
    -0.61
    requ
    -0.60
     ribbon
    -0.60
     disadvantage
    -0.58
     delay
    -0.58
    delay
    -0.58
    ypes
    -0.57
     disobedience
    -0.57
    ework
    -0.57
    thia
    -0.56
    POSITIVE LOGITS
     Views
    0.72
    è¦ļéĨĴ
    0.70
    ä½ľ
    0.70
     opinions
    0.70
    visor
    0.70
     reflections
    0.67
    editor
    0.67
     hers
    0.66
    Guest
    0.65
     views
    0.64
    Activations Density 0.092%

    No Known Activations