© 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. 92
    Prev
    Next
    INDEX
    Explanations

    phrases related to marking or designation

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring or grading systems

    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
     Kut
    -0.80
    ILLE
    -0.77
    rouch
    -0.65
     Lak
    -0.61
     Door
    -0.61
    abama
    -0.61
    agan
    -0.61
     brut
    -0.59
    SOURCE
    -0.58
    ourse
    -0.58
    POSITIVE LOGITS
    manship
    1.41
    eters
    1.16
    down
    1.14
    downs
    1.14
    eting
    1.02
     Twain
    1.01
    emark
    0.98
    ups
    0.93
    marks
    0.87
    eter
    0.86
    Activations Density 0.058%

    No Known Activations