© 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. 8-RES-JB
    11. 7048
    Prev
    Next
    INDEX
    Explanations

    phrases containing a form of the word "replied"

    oai_token-act-pair · gpt-3.5-turbo

    instances of dialogue or replies in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icipated
    -0.71
     Blazers
    -0.69
    enburg
    -0.68
    omic
    -0.64
    dar
    -0.64
    fi
    -0.63
    gotten
    -0.62
    mental
    -0.61
    effic
    -0.61
     Dracula
    -0.61
    POSITIVE LOGITS
     sarcast
    0.99
     angrily
    0.97
     affirm
    0.94
     politely
    0.87
     enthusiastically
    0.85
     thereto
    0.85
     favorably
    0.83
    reply
    0.81
    :]
    0.80
     emphatically
    0.79
    Activations Density 0.039%

    No Known Activations