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. 7-RES-JB
    6. 415
    Prev
    Next
    INDEX
    Explanations

    mentions of obtaining or possessing copies of various items or documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to copies of items or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atics
    -0.83
    urers
    -0.78
    Reviewer
    -0.77
    otics
    -0.76
    phasis
    -0.74
    zzle
    -0.72
    rh
    -0.72
    raq
    -0.70
     peg
    -0.70
     teasp
    -0.69
    POSITIVE LOGITS
     Quran
    0.85
     unpublished
    0.74
    DragonMagazine
    0.73
     Proceedings
    0.72
     PowerPoint
    0.72
     articles
    0.71
     documents
    0.70
     excerpts
    0.68
    written
    0.67
     copyrighted
    0.67
    Activations Density 0.118%

    No Known Activations