© 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. 10-RES-JB
    11. 18586
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical opinions and reviews

    oai_token-act-pair · gpt-3.5-turbo

    references to authority and opinions expressed in relation to ownership and representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agement
    -0.55
    çĶ°
    -0.50
     diplom
    -0.48
    ishable
    -0.48
    achus
    -0.47
    aging
    -0.47
    aged
    -0.47
    andum
    -0.47
    abee
    -0.47
     wink
    -0.45
    POSITIVE LOGITS
    kamp
    0.55
    Run
    0.51
    ainer
    0.51
    uden
    0.49
     //[
    0.47
    icz
    0.46
    onian
    0.45
     Simulator
    0.45
    oland
    0.45
    ways
    0.43
    Activations Density 0.260%

    No Known Activations