© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16094
    Prev
    Next
    INDEX
    Explanations

    prepositions or conjunctions followed by specific words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of time or location within a context

    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
    76561
    -0.67
     ®
    -0.67
    aic
    -0.65
    ãĤ´ãĥ³
    -0.64
    erenn
    -0.64
    ARE
    -0.64
     penned
    -0.63
    ä
    -0.63
    soever
    -0.62
    umed
    -0.61
    POSITIVE LOGITS
     terms
    1.23
     my
    1.14
     regards
    1.13
     somew
    1.09
     hindsight
    1.04
     retrospect
    1.01
     spite
    0.97
     relation
    0.97
    terms
    0.90
     vain
    0.88
    Activations Density 0.248%

    No Known Activations