© 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. 15724
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements and communications

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statements or quotes made by individuals

    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
    ;;;;;;;;;;;;
    -0.81
     dystopian
    -0.68
    ometimes
    -0.66
    Mp
    -0.66
     heroine
    -0.66
    chieve
    -0.64
    uyomi
    -0.64
    otin
    -0.64
    binding
    -0.63
     legalize
    -0.63
    POSITIVE LOGITS
     spokesman
    0.98
     spokeswoman
    0.97
    said
    0.94
     unnamed
    0.93
     spokesperson
    0.92
    quote
    0.84
     said
    0.83
    Asked
    0.83
     clarification
    0.78
     Said
    0.78
    Activations Density 0.485%

    No Known Activations