© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22492
    Prev
    Next
    INDEX
    Explanations

    words related to the term "positive."

    oai_token-act-pair · gpt-3.5-turbo

    words related to positivity and affirmative concepts

    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
     ANN
    -0.67
     arc
    -0.66
     YORK
    -0.61
     Wall
    -0.61
     runs
    -0.61
     run
    -0.60
     minutes
    -0.59
     ann
    -0.59
     running
    -0.58
     Brooks
    -0.58
    POSITIVE LOGITS
    itive
    4.75
    itives
    2.96
    itivity
    1.85
    itiveness
    1.81
    ition
    1.49
    itions
    1.44
    itative
    1.42
    itional
    1.40
    itance
    1.35
    itious
    1.27
    Activations Density 0.019%

    No Known Activations