© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17047
    Prev
    Next
    INDEX
    Explanations

    words related to oil drilling and wells

    oai_token-act-pair · gpt-3.5-turbo

    references to oil wells and groundwater

    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
    izophren
    -0.73
    REDACTED
    -0.72
     recogn
    -0.68
    âĶģ
    -0.68
    SHIP
    -0.66
    emonic
    -0.66
     Poe
    -0.64
     Pupp
    -0.63
     Nebula
    -0.61
    IENCE
    -0.60
    POSITIVE LOGITS
     drilled
    0.96
     wells
    0.91
    ards
    0.82
    inery
    0.81
    falls
    0.81
    field
    0.80
    chool
    0.79
    marks
    0.78
    lings
    0.78
    water
    0.75
    Activations Density 0.013%

    No Known Activations