© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    quotations and replies in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to quotes and replies in conversations

    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
    etting
    -0.75
    aucas
    -0.75
    gettable
    -0.73
     Rohing
    -0.71
     cellul
    -0.71
     spills
    -0.67
     volunte
    -0.66
     Palest
    -0.66
     spont
    -0.66
     therap
    -0.65
    POSITIVE LOGITS
     Originally
    0.84
     Investigator
    0.83
    Thread
    0.78
    --+
    0.75
     Quote
    0.73
    Quote
    0.73
     Preferences
    0.72
    estamp
    0.71
    ertodd
    0.70
    Activity
    0.68
    Activations Density 0.030%

    No Known Activations