© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6214
    Prev
    Next
    INDEX
    Explanations

    instances of the word "copy"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "copy" in various contexts

    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
    âĢİ
    -0.84
    ello
    -0.74
    spir
    -0.71
    ür
    -0.71
    âĢ
    -0.66
    bell
    -0.66
    ett
    -0.66
    ilton
    -0.65
    lees
    -0.65
    oret
    -0.65
    POSITIVE LOGITS
     copy
    3.88
     copies
    2.74
    copy
    2.64
     Copy
    2.61
     copying
    2.25
    Copy
    2.12
     copied
    2.04
     duplicate
    1.85
     duplication
    1.46
     photoc
    1.42
    Activations Density 0.007%

    No Known Activations