Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6786
    Prev
    Next
    INDEX
    Explanations

    phrases related to copying text or content

    oai_token-act-pair · gpt-3.5-turbo

    references to copying and duplicating content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.67
    doms
    -0.66
    stice
    -0.66
    ESCO
    -0.63
    oji
    -0.63
     tyr
    -0.62
    akh
    -0.62
     Anthrop
    -0.59
    alties
    -0.59
    astical
    -0.59
    POSITIVE LOGITS
    cat
    1.32
    cats
    1.26
     paste
    1.19
    writer
    1.11
    paste
    1.11
    editor
    1.09
    writers
    1.03
    edited
    1.03
    writing
    0.99
    write
    0.91
    Activations Density 0.037%

    No Known Activations