© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    words related to being unapologetic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to genetics and genetic 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
     angels
    -0.76
     millions
    -0.64
     loop
    -0.63
     mornings
    -0.63
     billions
    -0.62
     fallen
    -0.60
     mall
    -0.60
     cameras
    -0.60
     gif
    -0.59
     summer
    -0.59
    POSITIVE LOGITS
    etic
    4.72
    etics
    3.63
    etically
    3.38
    esis
    1.80
    etry
    1.56
    omic
    1.40
    eton
    1.33
    etric
    1.32
    esthetic
    1.25
    et
    1.21
    Activations Density 0.014%

    No Known Activations