© 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. 0-RES-JB
    11. 16668
    Prev
    Next
    INDEX
    Explanations

    the word "remainder"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remaining or leftover elements

    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
    arta
    -0.70
     incentiv
    -0.62
    omics
    -0.61
     upgr
    -0.61
    rises
    -0.60
    Scale
    -0.60
     slam
    -0.60
     quake
    -0.60
    iverse
    -0.60
    JUST
    -0.60
    POSITIVE LOGITS
     remainder
    2.73
     remaining
    2.16
     remnants
    1.80
     remnant
    1.65
     residual
    1.59
     residue
    1.42
     leftover
    1.39
     lingering
    1.32
     surviving
    1.10
     residues
    1.08
    Activations Density 0.022%

    No Known Activations