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. 9166
    Prev
    Next
    INDEX
    Explanations

    medical terms related to diagnosis or conditions that require a diagnosis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychiatric diagnoses and evaluations

    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
    orld
    -0.75
    tyard
    -0.74
    Ton
    -0.73
    hens
    -0.69
    ibur
    -0.68
     dstg
    -0.68
    velength
    -0.68
    hire
    -0.65
    perty
    -0.65
    ouver
    -0.65
    POSITIVE LOGITS
    ostic
    1.18
     diagnoses
    1.11
    ostics
    1.11
     diagnosis
    1.03
    osis
    0.91
    abetes
    0.90
     diagnosed
    0.89
     Diagn
    0.89
     clinically
    0.89
     epile
    0.86
    Activations Density 0.029%

    No Known Activations