© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    references to significant advancements or milestones

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "leap" in various contexts

    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
     ATF
    -0.68
    Chel
    -0.67
    bers
    -0.67
     SS
    -0.66
    ãĤ´
    -0.66
     COL
    -0.65
     Tex
    -0.65
     Collector
    -0.65
    ss
    -0.65
    adies
    -0.65
    POSITIVE LOGITS
     Leap
    3.97
     leap
    2.84
     leaps
    1.40
     leaping
    1.36
    hift
    1.07
     jump
    1.06
     leapt
    1.06
     pas
    0.95
     Hover
    0.92
    Jump
    0.92
    Activations Density 0.029%

    No Known Activations