© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2439
    Prev
    Next
    INDEX
    Explanations

    words related to grief and loss

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "brief."

    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
     bast
    -0.81
     gard
    -0.79
     cro
    -0.74
     inherit
    -0.72
     NCT
    -0.67
     apple
    -0.67
     antit
    -0.64
     gol
    -0.64
     colleg
    -0.64
     inher
    -0.63
    POSITIVE LOGITS
    rief
    3.79
    asket
    1.96
     Brief
    1.70
    rosse
    1.29
    reath
    1.14
    ombs
    1.05
    ODY
    1.00
    ASE
    0.97
    anking
    0.92
    rieving
    0.91
    Activations Density 0.029%

    No Known Activations