© 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. 8037
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "together" with varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "together" and related phrases emphasizing unity or collaboration

    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
    ista
    -0.76
    umbo
    -0.71
    geons
    -0.65
    ble
    -0.64
    unc
    -0.64
    geon
    -0.63
    ortal
    -0.63
    istas
    -0.63
    agnar
    -0.63
    ond
    -0.62
    POSITIVE LOGITS
    ness
    0.78
    ãĤ¤ãĥĪ
    0.75
    together
    0.69
    kson
    0.68
     prest
    0.66
    NESS
    0.66
     Kurd
    0.65
     together
    0.64
    nesses
    0.63
     constitute
    0.63
    Activations Density 0.038%

    No Known Activations