© 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. 1-RES-JB
    11. 10214
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the act of giving or contributing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "give" in various contexts indicating the act of providing or furnishing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.67
    377
    -0.63
    ROR
    -0.63
    Rated
    -0.63
     Nanto
    -0.61
    quished
    -0.61
    Page
    -0.60
    Can
    -0.60
     Cinema
    -0.59
    Boy
    -0.58
    POSITIVE LOGITS
    aways
    1.04
    away
    0.89
    hend
    0.80
     rise
    0.76
    give
    0.76
    pend
    0.75
     Pwr
    0.74
    pta
    0.73
     refunds
    0.73
    amaz
    0.72
    Activations Density 0.042%

    No Known Activations