© 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. 1-RES-JB
    11. 14374
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "said" in a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "said" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otion
    -0.76
    otin
    -0.75
    à¦
    -0.73
    pleting
    -0.69
    ooter
    -0.67
    anging
    -0.67
    estern
    -0.67
    PHOTOS
    -0.64
    email
    -0.63
    oked
    -0.63
    POSITIVE LOGITS
     anecd
    0.83
     bluntly
    0.80
     goodbye
    0.80
     sarcast
    0.79
    doms
    0.77
     afterward
    0.75
     afterwards
    0.69
     said
    0.68
     adam
    0.64
     Debor
    0.62
    Activations Density 0.206%

    No Known Activations