© 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. 11-RES-JB
    11. 5183
    Prev
    Next
    INDEX
    Explanations

    comparative adverbs indicating a higher degree or level of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.72
    OX
    -0.71
    abama
    -0.69
    hirt
    -0.66
    hyde
    -0.65
    utenberg
    -0.64
    DragonMagazine
    -0.63
    oice
    -0.63
    ibi
    -0.62
    acle
    -0.62
    POSITIVE LOGITS
     importantly
    1.76
     interestingly
    1.25
     specifically
    1.22
    so
    1.16
     controvers
    1.14
     omin
    1.13
     accurately
    1.13
     broadly
    1.10
     realistically
    1.06
     precisely
    1.02
    Activations Density 0.060%

    No Known Activations