© 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. 19178
    Prev
    Next
    INDEX
    Explanations

    words related to seeking relief or reprieve

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "retrieve."

    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
     capital
    -0.74
     hordes
    -0.67
     mold
    -0.64
     monopol
    -0.63
     flavored
    -0.62
     forums
    -0.61
     style
    -0.61
     advertisements
    -0.61
     copying
    -0.61
     pred
    -0.61
    POSITIVE LOGITS
    rieve
    4.62
    rieved
    2.57
    rieving
    2.36
    rie
    1.35
    iggle
    1.10
    ourning
    1.08
    terness
    1.01
    romy
    0.97
    rocal
    0.94
    ibble
    0.94
    Activations Density 0.022%

    No Known Activations