© 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. 10-RES-JB
    11. 13908
    Prev
    Next
    INDEX
    Explanations

    references to physical or metaphorical energy

    oai_token-act-pair · gpt-3.5-turbo

    references to energy and its various contexts or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.80
    ettings
    -0.79
    esi
    -0.76
    sonian
    -0.74
    esan
    -0.72
    izon
    -0.72
    igmat
    -0.71
    eryl
    -0.71
    gery
    -0.70
     Mock
    -0.70
    POSITIVE LOGITS
     expended
    0.98
     dissip
    0.88
     Enhancement
    0.86
     drinks
    0.85
     surges
    0.83
     depletion
    0.83
     metabolism
    0.82
     energy
    0.82
     drink
    0.81
    lifting
    0.80
    Activations Density 0.048%

    No Known Activations