© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14458
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and diagnoses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of diagnostic categories or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TING
    -0.72
    BOOK
    -0.72
    FORE
    -0.71
    ting
    -0.69
     Proposition
    -0.64
    ted
    -0.64
    DOM
    -0.64
    WHERE
    -0.61
     Shakespeare
    -0.61
    lihood
    -0.59
    POSITIVE LOGITS
    ostic
    1.33
    agn
    1.16
    ostics
    1.11
    ificent
    1.05
    ados
    1.00
    itude
    0.99
    osis
    0.90
    ocent
    0.89
    inen
    0.89
    agar
    0.86
    Activations Density 0.007%

    No Known Activations