© 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. 9-RES-JB
    11. 19475
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or addition of different elements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as well as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.76
    trap
    -0.67
    ======
    -0.63
    Kent
    -0.63
    NR
    -0.62
    /+
    -0.62
    itiveness
    -0.60
    \<
    -0.58
     COUR
    -0.58
    tein
    -0.57
    POSITIVE LOGITS
     well
    1.47
    well
    1.10
     opposed
    1.09
     evidenced
    1.05
    pects
    1.00
    pires
    0.95
     follows
    0.95
     diverse
    0.90
    pired
    0.90
     contrasted
    0.86
    Activations Density 0.135%

    No Known Activations