© 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. 7-RES-JB
    11. 1758
    Prev
    Next
    INDEX
    Explanations

    phrases related to influence, action, or requests, typically involving calling upon someone or something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "upon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.88
    BuyableInstoreAndOnline
    -0.76
    CT
    -0.75
    cell
    -0.68
     COP
    -0.68
    enegger
    -0.68
    ãĥ¼ãĤ¯
    -0.67
    UP
    -0.67
    GD
    -0.67
    Ó
    -0.66
    POSITIVE LOGITS
    ieth
    0.71
    erk
    0.67
     Presents
    0.65
     arrival
    0.65
    ignty
    0.64
     merit
    0.64
    !--
    0.63
     us
    0.63
    irin
    0.63
     acquaintance
    0.62
    Activations Density 0.028%

    No Known Activations