© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    mentions of accomplishments or notable events

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their performance

    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
    soType
    -0.89
     Solution
    -0.87
     GOODMAN
    -0.81
    ESE
    -0.77
    imentary
    -0.76
    olutions
    -0.72
    irtual
    -0.72
     Feedback
    -0.71
     Helpful
    -0.71
     Variant
    -0.71
    POSITIVE LOGITS
     langu
    1.29
     perenn
    1.28
     scarcely
    1.17
     barely
    1.16
     famously
    1.13
     hemorrh
    1.13
     arguably
    1.11
     reeling
    1.08
     racked
    1.08
     perpetually
    1.05
    Activations Density 0.328%

    No Known Activations