© 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. 7832
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting aside differences or personal interests for a greater cause

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to setting things aside or prioritizing other matters

    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
    gio
    -0.69
    KER
    -0.64
     promot
    -0.63
    ascus
    -0.62
    gging
    -0.61
    ifix
    -0.61
    ison
    -0.60
    inea
    -0.59
    gged
    -0.58
    atar
    -0.58
    POSITIVE LOGITS
    heid
    0.95
     aside
    0.78
     entirely
    0.74
     Unch
    0.73
     altogether
    0.72
    perty
    0.70
    thal
    0.70
    ancies
    0.66
    itures
    0.62
    urities
    0.62
    Activations Density 0.029%

    No Known Activations