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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 2675
    Prev
    Next
    INDEX
    Explanations

    references to power sources, specifically emphasizing coal-fired power plants and electricity generation

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of power generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.86
    odox
    -0.81
    erella
    -0.73
    gomery
    -0.72
    ĸļ
    -0.71
    antis
    -0.71
    azeera
    -0.70
     Kaufman
    -0.68
    PHOTOS
    -0.68
    atically
    -0.68
    POSITIVE LOGITS
    houses
    1.20
     stations
    1.15
     plants
    1.06
     grids
    1.01
     generators
    1.00
     outage
    0.96
     grid
    0.95
     Plants
    0.92
    plant
    0.91
     supply
    0.89
    Activations Density 0.050%

    No Known Activations