© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    products or items with a numerical value of '1' indicating popularity or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "1" followed by different contextual values

    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
    awaru
    -0.73
     Lumpur
    -0.73
    orative
    -0.64
    enges
    -0.61
    anty
    -0.60
    opy
    -0.60
    alus
    -0.59
    espie
    -0.59
     Pompe
    -0.59
    folk
    -0.59
    POSITIVE LOGITS
    Password
    1.27
    st
    1.27
    125
    1.22
    120
    1.20
    ½
    1.06
    128
    1.02
    000000
    0.99
    âģ
    0.99
    123
    0.87
    0000000
    0.86
    Activations Density 0.108%

    No Known Activations