© 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. 11-RES-JB
    11. 14840
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases related to various body parts and systems

    oai_token-act-pair · gpt-3.5-turbo

    references to medical conditions and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priceless
    -0.67
     srfAttach
    -0.66
     Bravo
    -0.66
     breeze
    -0.65
     payload
    -0.65
     offering
    -0.64
     tame
    -0.63
     instructional
    -0.63
     widgets
    -0.63
     liberating
    -0.63
    POSITIVE LOGITS
    itis
    1.21
    inflamm
    1.19
    thritis
    1.18
    emia
    1.16
    esthesia
    1.16
    iasis
    1.16
    ascular
    1.14
    ocard
    1.14
    algia
    1.14
     pneumonia
    1.13
    Activations Density 0.136%

    No Known Activations