© 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. 6-RES-JB
    11. 10689
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or entity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Der"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.67
    INTER
    -0.66
     Elephant
    -0.65
    odcast
    -0.63
    toggle
    -0.62
     [|
    -0.62
    hetti
    -0.61
    ZI
    -0.61
     Fenrir
    -0.60
    ships
    -0.59
    POSITIVE LOGITS
    ricks
    1.08
    bys
    1.04
    ivation
    0.99
    ived
    0.87
    bil
    0.87
    rick
    0.86
    ription
    0.84
     Spiegel
    0.84
    rek
    0.82
    cliffe
    0.81
    Activations Density 0.021%

    No Known Activations