© 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. 14677
    Prev
    Next
    INDEX
    Explanations

    words related to sizes or rankings, specifically the term "largest"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating size rankings among entities or categories

    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
     Cour
    -0.75
     course
    -0.73
     psych
    -0.71
     intro
    -0.71
     courses
    -0.71
     reactive
    -0.71
     field
    -0.71
     written
    -0.69
     personal
    -0.69
     nin
    -0.69
    POSITIVE LOGITS
    largest
    3.18
    highest
    1.73
    big
    1.44
    most
    1.44
    worst
    1.36
    latest
    1.27
    best
    1.21
    larg
    1.20
    huge
    1.15
    glomer
    1.13
    Activations Density 0.017%

    No Known Activations