© 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. 4-RES-JB
    11. 7565
    Prev
    Next
    INDEX
    Explanations

    instances of the word "photocopy" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visual or physical representation, particularly in the context of photocopying and imagery

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

    No Comments

    Negative Logits
    erness
    -0.99
    ault
    -0.88
    geant
    -0.83
    ream
    -0.83
    iator
    -0.83
    ellation
    -0.78
    ius
    -0.78
    inctions
    -0.77
    emy
    -0.75
    iments
    -0.73
    POSITIVE LOGITS
    女
    0.91
     Uz
    0.88
    é¾įå
    0.85
    ãģ¾
    0.78
    ãĤ¢ãĥ«
    0.77
    uddin
    0.73
    ãģł
    0.70
     cough
    0.68
    MET
    0.68
    代
    0.68
    Activations Density 0.044%

    No Known Activations