Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1816
    Prev
    Next
    INDEX
    Explanations

    keywords specifically marked by "Ċ" which are likely used in a specific context like section headers or article titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of subscription-related phrases or calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reneg
    -0.67
     sessions
    -0.64
     Malta
    -0.64
     placement
    -0.63
     arbit
    -0.63
     Quad
    -0.62
     pc
    -0.62
     sails
    -0.61
     deceived
    -0.61
     RX
    -0.60
    POSITIVE LOGITS
    WASHINGTON
    1.04
    Few
    0.95
    SHARE
    0.95
    LESS
    0.90
    Imagine
    0.89
    DES
    0.88
    Warning
    0.87
    ccording
    0.87
    Copyright
    0.86
    Contribut
    0.86
    Activations Density 0.083%

    No Known Activations