© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    portions of text addressing or referring to the reader

    oai_token-act-pair · gpt-3.5-turbo

    references to the audience or reader

    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
    ipal
    -0.90
    ĸļ
    -0.77
    entimes
    -0.74
     Canaver
    -0.72
    icy
    -0.69
    ice
    -0.67
    unic
    -0.66
    arc
    -0.64
    ayne
    -0.64
    emon
    -0.63
    POSITIVE LOGITS
     guys
    1.36
     yourselves
    1.26
    tub
    1.26
     gentlemen
    1.07
    RS
    0.94
    're
    0.88
    Tube
    0.88
     sir
    0.86
     yourself
    0.85
     ladies
    0.81
    Activations Density 0.162%

    No Known Activations