© 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. 8-RES-JB
    11. 343
    Prev
    Next
    INDEX
    Explanations

    phrases related to "mind-boggling" occurrences or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cognitive concepts and mental phenomena, especially those that imply complexity or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.73
    ansas
    -0.66
    DN
    -0.65
     (>
    -0.64
    SHA
    -0.63
    ozo
    -0.62
    avorite
    -0.61
    estone
    -0.61
    minster
    -0.60
     Bold
    -0.59
    POSITIVE LOGITS
    apse
    0.71
    ²¾
    0.65
    asers
    0.65
    condition
    0.65
     McAuliffe
    0.64
    otion
    0.63
     Haas
    0.62
     Gork
    0.61
    eering
    0.60
    xiety
    0.60
    Activations Density 0.132%

    No Known Activations