© 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. 2-RES-JB
    11. 3217
    Prev
    Next
    INDEX
    Explanations

    adverbs emphasizing a magical or mysterious aspect

    oai_token-act-pair · gpt-3.5-turbo

    terms that imply sudden or extraordinary changes, often with a sense of convenience or mystery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ger
    -0.73
     intentions
    -0.70
     resolutions
    -0.69
    gers
    -0.68
     preparations
    -0.68
    ges
    -0.68
    ties
    -0.66
     thoughts
    -0.66
     skepticism
    -0.66
     Values
    -0.65
    POSITIVE LOGITS
    ufact
    0.82
    icably
    0.80
     housed
    0.80
    orpor
    0.79
    UNCH
    0.77
     endowed
    0.76
     allocated
    0.76
     regenerate
    0.76
     rebuilt
    0.76
     transported
    0.75
    Activations Density 0.017%

    No Known Activations