© 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. 6-RES-JB
    11. 17331
    Prev
    Next
    INDEX
    Explanations

    lawyers or legal professionals who are mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" as a reference to individuals involved in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Georg
    -0.77
    ³³³³
    -0.72
    urg
    -0.65
    Weak
    -0.63
     barbaric
    -0.63
     proving
    -0.62
     unacceptable
    -0.62
     Gothic
    -0.61
     Bound
    -0.61
     showing
    -0.61
    POSITIVE LOGITS
     oversaw
    0.98
     redes
    0.94
     oversees
    0.91
     specialize
    0.87
    etz
    0.86
     superv
    0.84
    veland
    0.84
    ©¶æ
    0.83
     accomp
    0.82
     livest
    0.82
    Activations Density 0.103%

    No Known Activations