© 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. 8-RES-JB
    11. 24125
    Prev
    Next
    INDEX
    Explanations

    references to capsules, submarines, and aircraft

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aviation, submarines, and capsules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beer
    -0.83
    ithing
    -0.81
    WORK
    -0.80
    chest
    -0.71
    lder
    -0.69
    place
    -0.69
    Beer
    -0.69
    iard
    -0.68
     Sabbath
    -0.66
    bell
    -0.65
    POSITIVE LOGITS
    ules
    0.90
    ule
    0.85
    insula
    0.85
    ilant
    0.79
    iaries
    0.78
    endiary
    0.77
    adian
    0.75
    udeau
    0.75
    aeus
    0.73
    ratulations
    0.73
    Activations Density 0.124%

    No Known Activations