© 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. 0-RES-JB
    11. 7586
    Prev
    Next
    INDEX
    Explanations

    copies of items in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to copies of media or published works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mund
    -0.72
    anna
    -0.69
    âĢİ
    -0.68
    undrum
    -0.67
     vein
    -0.67
    adi
    -0.67
    camp
    -0.66
     framework
    -0.64
    Bridge
    -0.63
    Connector
    -0.63
    POSITIVE LOGITS
     copies
    4.02
     copy
    2.48
    copy
    1.96
     Copy
    1.93
     copying
    1.77
     copied
    1.63
    Copy
    1.62
     versions
    1.61
     originals
    1.53
     clones
    1.44
    Activations Density 0.007%

    No Known Activations