© 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 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. 4-RES-JB
    11. 16762
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ther" and variations of it like "ether" and "further"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the syllable "ther" and its context in different words

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

    No Comments

    Negative Logits
    ELS
    -0.92
    URI
    -0.73
     Strauss
    -0.69
    ured
    -0.62
     Chao
    -0.62
     Peel
    -0.60
     Lomb
    -0.59
     Wilde
    -0.59
    000000
    -0.59
    REC
    -0.58
    POSITIVE LOGITS
    apy
    1.37
    idge
    1.11
    apist
    1.09
    swer
    1.07
    netic
    1.00
    ther
    1.00
    nian
    0.97
    mal
    0.90
    soever
    0.89
    apter
    0.87
    Activations Density 0.012%

    No Known Activations