© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    words related to the Dakota Access Pipeline controversy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Dakota" related to the Dakota Access Pipeline

    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
    atics
    -0.76
    =-=-=-=-=-=-=-=-
    -0.74
    isations
    -0.70
    istics
    -0.70
     pse
    -0.68
     Notting
    -0.67
     streng
    -0.67
     destro
    -0.65
    ecast
    -0.64
    ################
    -0.63
    POSITIVE LOGITS
     Dakota
    0.97
     Sioux
    0.80
     Nickel
    0.79
     Rapids
    0.77
     State
    0.73
     Territory
    0.73
     Springs
    0.72
    grass
    0.70
     Railroad
    0.70
    inois
    0.68
    Activations Density 0.004%

    No Known Activations