© 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. 3-RES-JB
    11. 1769
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Raw" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to WWE Raw and related events or episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.81
    mercial
    -0.78
    uate
    -0.76
    ortium
    -0.76
    repre
    -0.75
    uated
    -0.75
    uration
    -0.73
    uppet
    -0.71
    awaru
    -0.71
    ittees
    -0.70
    POSITIVE LOGITS
    lings
    1.24
    hide
    1.12
    ls
    1.08
    lins
    1.04
    Raw
    0.94
    leigh
    0.93
    esome
    0.89
    Skin
    0.85
    kus
    0.85
     Raw
    0.84
    Activations Density 0.009%

    No Known Activations