© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    references to tar sands, organizations related to tar sands activism, and geographical locations related to tar sands

    oai_token-act-pair · gpt-3.5-turbo

    references to tar sands

    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
    istically
    -0.77
     Hancock
    -0.75
    VP
    -0.74
    ISON
    -0.71
    ishable
    -0.70
    named
    -0.70
    WT
    -0.70
    ivia
    -0.69
    Wilson
    -0.69
    Reviewer
    -0.68
    POSITIVE LOGITS
     sands
    1.20
    roleum
    0.81
     wast
    0.71
     oils
    0.70
     Sands
    0.70
    cape
    0.70
    lash
    0.69
     wastes
    0.69
     glands
    0.68
     stockp
    0.65
    Activations Density 0.009%

    No Known Activations