© 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. 9-RES-JB
    11. 14865
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and advancements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific assessments and evaluations

    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
     gladly
    -0.81
    Show
    -0.76
    !.
    -0.74
    ISTORY
    -0.72
     accordingly
    -0.72
    Truth
    -0.72
    !/
    -0.71
    agree
    -0.70
     entert
    -0.70
    swer
    -0.69
    POSITIVE LOGITS
     Fukushima
    1.26
     radioactive
    1.11
     debris
    1.07
     wastewater
    1.05
     satellites
    1.04
     plutonium
    1.04
     aircraft
    1.03
     earthquakes
    1.02
     comet
    1.00
     graphene
    1.00
    Activations Density 1.126%

    No Known Activations