© 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. 17573
    Prev
    Next
    INDEX
    Explanations

    sentences describing a specific action or process that is part of a larger activity or project

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating components or elements of larger contexts or systems

    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
    oir
    -0.77
     Appears
    -0.72
    books
    -0.69
    ocry
    -0.67
    usercontent
    -0.66
     lied
    -0.66
    iste
    -0.63
    ozyg
    -0.63
     bugs
    -0.62
    houses
    -0.62
    POSITIVE LOGITS
     preparations
    0.93
     ongoing
    0.93
    interstitial
    0.88
    Operation
    0.83
     Operation
    0.81
     broader
    0.80
     efforts
    0.79
     celebrations
    0.75
     its
    0.74
     precaution
    0.73
    Activations Density 0.091%

    No Known Activations