© 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. 10-RES-JB
    11. 10272
    Prev
    Next
    INDEX
    Explanations

    names or handles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    usernames or handles linked to social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Disorder
    -0.91
     Society
    -0.90
     Goddess
    -0.89
     Ninth
    -0.88
     Dimension
    -0.86
     Characters
    -0.86
     Association
    -0.86
     Insurance
    -0.82
     Zombies
    -0.82
     Stamina
    -0.82
    POSITIVE LOGITS
    jamin
    1.19
    maxwell
    1.18
    bryce
    1.15
    _
    1.11
    olson
    1.07
    john
    1.05
    othy
    0.96
    reports
    0.96
    lynn
    0.93
    brown
    0.93
    Activations Density 0.065%

    No Known Activations