© 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. 9-RES-JB
    11. 15678
    Prev
    Next
    INDEX
    Explanations

    medical terms and related information, such as hospital records and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to medical or legal documentation and records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.75
    !/
    -0.74
    rossover
    -0.72
    ageddon
    -0.71
    humans
    -0.70
    uador
    -0.66
    uitous
    -0.65
    hesda
    -0.64
    DoS
    -0.63
     leaps
    -0.63
    POSITIVE LOGITS
     diary
    1.60
     notebook
    1.46
     broch
    1.45
     ledger
    1.45
     journals
    1.44
     notebooks
    1.44
     documents
    1.44
     manuals
    1.42
     booklet
    1.40
     journal
    1.35
    Activations Density 1.246%

    No Known Activations