© 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. 18255
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stuffed", and to a lesser extent, related terms such as "plush" and "eddy"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being filled or crammed with items or materials

    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
    nm
    -0.84
    asons
    -0.70
    urity
    -0.68
     Views
    -0.67
    cloud
    -0.66
    axis
    -0.65
     Spart
    -0.65
    properties
    -0.65
    MW
    -0.64
    Rate
    -0.64
    POSITIVE LOGITS
     stuffed
    3.56
     stuffing
    2.21
     plush
    1.59
     tucked
    1.42
     crammed
    1.36
     shoved
    1.20
    eddy
    1.10
     Teddy
    1.10
     floppy
    1.08
     stash
    1.05
    Activations Density 0.040%

    No Known Activations