© 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. 9-RES-JB
    11. 7596
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes with an emphasis on comparison

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration or appreciation for art and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pause
    -0.84
     Rasmussen
    -0.77
    iatus
    -0.77
    anwhile
    -0.76
    erity
    -0.73
     Delay
    -0.72
    delay
    -0.71
    pmwiki
    -0.71
    izons
    -0.71
     administrations
    -0.70
    POSITIVE LOGITS
     recognizable
    1.20
     beautiful
    1.17
     hideous
    1.14
     gorgeous
    1.11
     resemble
    1.10
     aest
    1.08
     resemb
    1.06
     cute
    1.06
     resembling
    1.06
     adorable
    1.05
    Activations Density 0.580%

    No Known Activations