© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22505
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific concepts and advancements

    oai_token-act-pair · gpt-3.5-turbo

    the concept and references to science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seasons
    -0.75
    leased
    -0.69
    zik
    -0.68
     Arrows
    -0.67
    ividual
    -0.67
    upon
    -0.66
    pora
    -0.66
    ometown
    -0.66
    nants
    -0.66
    inately
    -0.64
    POSITIVE LOGITS
     fiction
    1.22
     Fiction
    0.98
     science
    0.92
    science
    0.86
     sciences
    0.85
    mong
    0.80
    fiction
    0.79
     educator
    0.78
    craft
    0.78
    natureconservancy
    0.77
    Activations Density 0.021%

    No Known Activations