© 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. 4-RES-JB
    11. 11200
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomy

    oai_token-act-pair · gpt-3.5-turbo

    references to astronomy and related scientific organizations

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

    No Comments

    Negative Logits
    BACK
    -0.71
     Snyder
    -0.69
    nir
    -0.67
     Feld
    -0.66
    dos
    -0.65
    theless
    -0.65
    upon
    -0.63
    do
    -0.62
    witz
    -0.62
    taker
    -0.61
    POSITIVE LOGITS
    omical
    1.46
    omy
    1.20
    autical
    1.17
    auts
    1.10
    aut
    0.97
    igmatic
    0.93
    mosp
    0.92
    ollo
    0.90
    elong
    0.88
    eteen
    0.88
    Activations Density 0.009%

    No Known Activations