© 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. 13939
    Prev
    Next
    INDEX
    Explanations

    phrases indicating deep contemplation or significant thought about a specific subject

    oai_token-act-pair · gpt-3.5-turbo

    references to "it" in various contexts of decision-making or thoughts

    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
    agogue
    -0.61
     Vehicle
    -0.61
    abee
    -0.57
     Plate
    -0.57
    arthed
    -0.57
     Firm
    -0.56
    oided
    -0.56
    dp
    -0.55
     Colo
    -0.55
    quartered
    -0.54
    POSITIVE LOGITS
    chy
    1.22
     happening
    1.06
    alian
    1.01
    self
    0.93
    iner
    0.87
    unes
    0.85
     myself
    0.81
     afterwards
    0.81
     happen
    0.79
    displayText
    0.79
    Activations Density 0.120%

    No Known Activations