© 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. 1-RES-JB
    11. 10441
    Prev
    Next
    INDEX
    Explanations

    words related to salary caps

    oai_token-act-pair · gpt-3.5-turbo

    capitalization patterns, particularly focusing on the word "cap" and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.89
     normalized
    -0.70
     separate
    -0.65
     competitive
    -0.59
     NE
    -0.59
     STEP
    -0.59
     boxed
    -0.58
     unexplained
    -0.58
     bri
    -0.58
     intimidated
    -0.57
    POSITIVE LOGITS
    cap
    1.44
    itol
    1.18
    itals
    1.16
    acity
    1.13
    abilities
    1.05
    caps
    1.04
    illary
    1.02
    Cap
    1.01
    incinn
    0.94
    iment
    0.94
    Activations Density 0.003%

    No Known Activations