© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    emotional reactions involving the gut, such as strong emotions or impact

    oai_token-act-pair · gpt-3.5-turbo

    references to intense emotional experiences or physical sensations, particularly related to the gut

    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
    hips
    -0.80
     Stephenson
    -0.75
     Chains
    -0.74
    hift
    -0.70
     Aad
    -0.69
    hare
    -0.65
     Sins
    -0.64
    eton
    -0.64
    cale
    -0.62
     Kingdoms
    -0.62
    POSITIVE LOGITS
    ierrez
    1.25
    ted
    1.23
    ting
    1.10
    ters
    1.07
    tering
    1.01
    tered
    0.98
    rition
    0.98
    warts
    0.92
    lig
    0.91
    osc
    0.90
    Activations Density 0.051%

    No Known Activations