© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 221
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of various actions or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worse
    -0.75
     Worse
    -0.65
    ById
    -0.65
     sued
    -0.65
     tempted
    -0.63
    Radio
    -0.61
    MpServer
    -0.61
     slumped
    -0.61
     CLSID
    -0.60
     remotely
    -0.60
    POSITIVE LOGITS
     emphas
    0.95
     clarify
    0.85
     vigilance
    0.84
     ensure
    0.84
     remember
    0.84
     emphasize
    0.83
     preserving
    0.81
     ensuring
    0.81
     remembering
    0.80
     understand
    0.80
    Activations Density 0.166%

    No Known Activations