© 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 EvalsExportsinterp-engineNEWAPI 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. 11015
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a transition or shift in focus

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "when it comes to."

    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
    arious
    -0.85
    letter
    -0.79
    ©¶æ¥µ
    -0.78
    istas
    -0.77
     teasp
    -0.76
    icer
    -0.76
    plus
    -0.76
    avi
    -0.75
    NES
    -0.75
    horn
    -0.75
    POSITIVE LOGITS
     selecting
    1.17
     determining
    1.15
     evaluating
    1.13
     preserving
    1.11
     assessing
    1.10
     dealing
    1.07
     deciding
    1.05
     resolving
    1.05
     figuring
    1.05
     protecting
    1.04
    Activations Density 0.083%

    No Known Activations