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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 14760
    Prev
    Next
    INDEX
    Explanations

    the word "ole" at varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities associated with authority or significant roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lished
    -0.73
    è¦ļéĨĴ
    -0.67
    é¾
    -0.66
    ensical
    -0.64
    wcsstore
    -0.64
    ultan
    -0.62
    izoph
    -0.61
    DERR
    -0.60
    raints
    -0.59
     AQ
    -0.59
    POSITIVE LOGITS
    tta
    1.20
    tto
    1.20
    tti
    1.14
    lette
    1.04
    cule
    1.00
    cules
    0.98
    ole
    0.95
    ttes
    0.89
    cular
    0.88
    estyle
    0.79
    Activations Density 0.008%

    No Known Activations