© 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. 0-RES-JB
    11. 5336
    Prev
    Next
    INDEX
    Explanations

    words related to fossil fuel extraction, particularly shale gas and limestone

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shale gas and related geological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anners
    -0.80
     AN
    -0.78
    AD
    -0.73
     Commun
    -0.69
    Card
    -0.68
     ACT
    -0.67
     av
    -0.67
     Asgard
    -0.67
     AD
    -0.66
    vv
    -0.66
    POSITIVE LOGITS
     shale
    3.83
     limestone
    1.39
     geological
    1.24
     granite
    1.11
     OPEC
    1.09
     methane
    1.07
     sands
    1.07
     fracking
    1.06
     drilling
    0.99
     Lime
    0.97
    Activations Density 0.028%

    No Known Activations