© 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. 1-RES-JB
    11. 24048
    Prev
    Next
    INDEX
    Explanations

    instances of text duplication or plagiarism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to copying and plagiarism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthrop
    -0.76
    ving
    -0.71
    croft
    -0.71
    Dispatch
    -0.65
    ALE
    -0.63
    pora
    -0.63
     Sinai
    -0.63
     Redemption
    -0.62
    esa
    -0.60
    Parameter
    -0.60
    POSITIVE LOGITS
     copied
    1.30
     copying
    1.01
     copy
    0.93
     copies
    0.87
    chin
    0.84
     Copy
    0.82
     Gutenberg
    0.80
     paste
    0.78
    urally
    0.78
    smanship
    0.74
    Activations Density 0.011%

    No Known Activations