© 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. 9-RES-JB
    11. 15790
    Prev
    Next
    INDEX
    Explanations

    quotations or statements made by a specific person

    oai_token-act-pair · gpt-3.5-turbo

    statements related to personal achievements and political rhetoric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hels
    -0.92
     CLR
    -0.82
     partName
    -0.77
     Canon
    -0.77
    etheless
    -0.76
     Wilde
    -0.70
    byss
    -0.69
     Vor
    -0.69
     Nou
    -0.68
     Quadro
    -0.68
    POSITIVE LOGITS
    TRUMP
    1.21
    Hillary
    1.18
    DonaldTrump
    1.07
    America
    1.04
     Hillary
    1.00
    Donald
    0.98
     AMERICA
    0.98
    President
    0.94
    Congress
    0.93
    Trump
    0.92
    Activations Density 0.453%

    No Known Activations