© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18949
    Prev
    Next
    INDEX
    Explanations

    words related to rapid increase, such as 'soared', 'skyrocketed', and 'surged'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant increases in value or amounts

    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
    itu
    -0.65
    nothing
    -0.65
    finished
    -0.64
    tta
    -0.64
    tein
    -0.63
    fact
    -0.63
    nda
    -0.62
    Nap
    -0.62
     tac
    -0.61
    bad
    -0.61
    POSITIVE LOGITS
     upward
    0.86
     exponentially
    0.85
     astron
    0.83
     upwards
    0.79
     overnight
    0.79
     popularity
    0.78
     leaps
    0.77
     into
    0.74
     ahead
    0.72
    uating
    0.69
    Activations Density 0.094%

    No Known Activations