© 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. 7-RES-JB
    11. 12389
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that justify or defend a decision

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence breaks

    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
     thrill
    -0.65
     unicorn
    -0.62
    plet
    -0.62
     oath
    -0.61
    itialized
    -0.61
     strap
    -0.60
     awesome
    -0.60
    ersive
    -0.60
    ierre
    -0.59
     planet
    -0.59
    POSITIVE LOGITS
    Newsletter
    1.39
    Advertisement
    0.98
    Similarly
    0.95
    Finally
    0.91
    Copyright
    0.90
    Meanwhile
    0.89
    Lastly
    0.87
    VERTISEMENT
    0.87
    Write
    0.87
    Still
    0.85
    Activations Density 0.514%

    No Known Activations