© 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. 22059
    Prev
    Next
    INDEX
    Explanations

    specific events or occurrences mentioned in a textual passage

    oai_token-act-pair · gpt-3.5-turbo

    references to specific occurrences or happenings

    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
    geon
    -0.84
    heid
    -0.74
    culosis
    -0.73
    efficiency
    -0.71
    cott
    -0.69
    inately
    -0.69
    oise
    -0.68
    geons
    -0.68
    BSD
    -0.66
    lication
    -0.65
    POSITIVE LOGITS
     unfolding
    1.49
     transpired
    1.40
     unfold
    1.35
     unfolded
    1.28
     occurring
    1.20
     surrounding
    1.16
     involving
    1.03
     depicted
    1.02
     happening
    1.00
     leading
    0.99
    Activations Density 0.165%

    No Known Activations