© 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. 9-RES-JB
    11. 15586
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain the word "the" and other determiners, indicating a focus on specific mentions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.94
    leground
    -0.92
    LEASE
    -0.90
    ornings
    -0.82
    2020
    -0.79
    APD
    -0.78
    LCS
    -0.77
    amic
    -0.77
    atellite
    -0.77
     UNCLASSIFIED
    -0.76
    POSITIVE LOGITS
     simplest
    1.07
     idea
    1.06
     slightest
    1.06
     easiest
    1.03
     term
    1.01
    oret
    0.99
     wearer
    0.99
     drawback
    0.97
     earliest
    0.96
     downside
    0.95
    Activations Density 0.562%

    No Known Activations