© 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. 10-RES-JB
    11. 18663
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that occur after a specific event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.79
    lly
    -0.78
    ãĥ¯
    -0.70
    cially
    -0.68
     Tradable
    -0.67
    zbek
    -0.67
    <?
    -0.67
    cial
    -0.66
    âĺ
    -0.66
    ASON
    -0.65
    POSITIVE LOGITS
     initial
    1.08
     completion
    1.05
     debacle
    1.03
     expiration
    1.00
     conclusion
    0.96
     departure
    0.95
     onset
    0.94
     breakup
    0.94
     fact
    0.93
     incident
    0.90
    Activations Density 0.082%

    No Known Activations