© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5318
    Prev
    Next
    INDEX
    Explanations

    words related to energizing and revitalizing actions or states

    oai_token-act-pair · gpt-3.5-turbo

    terms related to energy, motivation, and emotional states

    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
    REE
    -0.70
     LCS
    -0.68
     deviations
    -0.68
     OW
    -0.68
     Prob
    -0.66
     decimal
    -0.66
     Clerk
    -0.66
     loophole
    -0.65
     loopholes
    -0.65
     prediction
    -0.63
    POSITIVE LOGITS
    izing
    1.56
    ized
    1.56
    ization
    1.43
    ised
    1.40
    ising
    1.39
    izational
    1.38
    isation
    1.29
    izer
    1.26
    izable
    1.21
    izers
    1.21
    Activations Density 0.074%

    No Known Activations