© 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. 4-RES-JB
    11. 16401
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and terms, especially those ending in 'otic', 'ic', or 'ogenetic'

    oai_token-act-pair · gpt-3.5-turbo

    words related to biochemical and medical terms, particularly those ending with specific suffixes

    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
    wright
    -0.82
    flies
    -0.82
    matched
    -0.79
    fully
    -0.79
    clips
    -0.79
    bourg
    -0.74
    IRD
    -0.72
    erves
    -0.72
    edin
    -0.72
    knit
    -0.72
    POSITIVE LOGITS
     acid
    1.00
    otin
    0.87
     tendencies
    0.79
     zeal
    0.72
    ity
    0.71
     retreat
    0.71
     Tend
    0.70
     cleansing
    0.70
    raft
    0.69
     resusc
    0.68
    Activations Density 0.034%

    No Known Activations