© 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. 11-RES-JB
    11. 6627
    Prev
    Next
    INDEX
    Explanations

    words related to food and cooking

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to risks and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Frag
    -0.81
    ité
    -0.73
    agus
    -0.72
    itter
    -0.71
    ift
    -0.69
    ogy
    -0.68
    URR
    -0.67
    mare
    -0.67
    ifier
    -0.64
    AG
    -0.64
    POSITIVE LOGITS
     additionally
    0.87
     unspecified
    0.77
     similarly
    0.76
     assorted
    0.75
     obviously
    0.75
     predominantly
    0.75
     alternatively
    0.75
     likewise
    0.73
     curiously
    0.73
     necessarily
    0.73
    Activations Density 0.207%

    No Known Activations