© 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. 15638
    Prev
    Next
    INDEX
    Explanations

    medical conditions or related terms, including "Polycystic Ovarian Syndrome" and "cytokinesis"

    oai_token-act-pair · gpt-3.5-turbo

    references to cyclical phenomena or conditions

    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
     Jinn
    -0.72
     indo
    -0.70
    FontSize
    -0.68
    erer
    -0.63
     relativity
    -0.62
    IFIED
    -0.61
    Reviewed
    -0.61
    METHOD
    -0.61
    handler
    -0.60
    erers
    -0.59
    POSITIVE LOGITS
    cling
    1.41
    prus
    1.14
    cled
    1.03
    cles
    0.99
    stic
    0.84
    DAY
    0.83
    clone
    0.82
    nergy
    0.81
    pter
    0.81
    ohyd
    0.81
    Activations Density 0.007%

    No Known Activations