© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a high level of quality or skill

    oai_token-act-pair · gpt-3.5-turbo

    the term "highly" followed by various qualifiers indicating a degree of intensity or quality

    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
     Turns
    -0.74
    arations
    -0.68
    Shape
    -0.66
    ength
    -0.66
    save
    -0.65
    ette
    -0.64
    rev
    -0.64
    vention
    -0.64
    olon
    -0.63
    answer
    -0.63
    POSITIVE LOGITS
     highly
    3.18
    highly
    2.45
     Highly
    2.20
     strongly
    1.79
     extremely
    1.64
     hugely
    1.61
     deeply
    1.54
     heavily
    1.49
     hotly
    1.46
     intensely
    1.45
    Activations Density 0.016%

    No Known Activations