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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 394
    Prev
    Next
    INDEX
    Explanations

    words related to ophthalmology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the suffix "oph" typical in scientific or medical terminology

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

    No Comments

    Negative Logits
    forth
    -0.76
    WARD
    -0.76
     Gemini
    -0.75
    nels
    -0.69
    LOAD
    -0.69
     Crescent
    -0.66
    LESS
    -0.65
     Clarks
    -0.64
    FIN
    -0.64
     Sox
    -0.63
    POSITIVE LOGITS
    osph
    1.35
    osate
    1.32
    oph
    1.27
    ouse
    1.18
    omore
    1.06
    agic
    1.04
    obe
    1.04
    antom
    1.03
    ilic
    1.03
    obia
    1.03
    Activations Density 0.011%

    No Known Activations