© 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. 11-RES-JB
    11. 6599
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izable
    -0.69
    Duration
    -0.66
    glers
    -0.65
     kW
    -0.64
     certs
    -0.63
    encies
    -0.63
    Adds
    -0.62
    ottage
    -0.62
     compromises
    -0.60
    Prev
    -0.60
    POSITIVE LOGITS
     born
    1.13
     fortunate
    1.10
     browsing
    1.08
     wondering
    1.06
     chatting
    1.05
     amazed
    1.01
     intrigued
    0.97
     researching
    0.96
     lucky
    0.96
     invited
    0.96
    Activations Density 0.177%

    No Known Activations