Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14080
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking a strong stance or standing up for something

    oai_token-act-pair · gpt-3.5-turbo

    instances where the phrase "stand up" is used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     understatement
    -0.73
    neau
    -0.70
     CLSID
    -0.68
    mes
    -0.65
    MH
    -0.64
     Destination
    -0.63
     Ruin
    -0.63
    allo
    -0.62
     Clicker
    -0.61
    Lot
    -0.60
    POSITIVE LOGITS
     against
    0.85
    stairs
    0.83
    ris
    0.81
     paddle
    0.80
     comedians
    0.75
     Against
    0.74
    ices
    0.71
    river
    0.71
    atoon
    0.71
     comedian
    0.71
    Activations Density 0.033%

    No Known Activations