© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by pronouns or nouns

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "to" in various contexts

    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
    ahime
    -0.64
     thereto
    -0.62
    cyclop
    -0.62
    é¾įåĸļ士
    -0.62
    motion
    -0.60
    VERTISEMENT
    -0.59
    runs
    -0.59
    empl
    -0.58
    buster
    -0.58
     handled
    -0.57
    POSITIVE LOGITS
    pless
    1.13
    ilet
    0.98
     me
    0.97
    wered
    0.97
     justify
    0.94
     imply
    0.92
    psy
    0.92
    ggles
    0.91
     provoke
    0.87
     appease
    0.87
    Activations Density 0.152%

    No Known Activations