© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24538
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of renewable energy sources, particularly solar and wind energy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to renewable energy sources and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parents
    -0.90
     Winners
    -0.85
    ĸļ
    -0.79
     Faces
    -0.75
    Words
    -0.75
    OVER
    -0.75
    ername
    -0.74
    Winner
    -0.73
    ilege
    -0.73
    Win
    -0.72
    POSITIVE LOGITS
     biomass
    1.38
     tidal
    1.36
     solar
    1.33
     hydro
    1.25
     hydrogen
    1.15
     wind
    1.14
     hyd
    1.13
     thermal
    1.10
     biod
    1.09
     renewables
    1.08
    Activations Density 0.149%

    No Known Activations