© 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 EvalsExportsinterp-engineNEWAPI 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. 18926
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of sending something

    oai_token-act-pair · gpt-3.5-turbo

    the word "sent" and its variations in context, particularly regarding communication or transfer

    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
    theless
    -0.77
    orsi
    -0.64
    walker
    -0.63
     Tune
    -0.63
    Enough
    -0.62
    kernel
    -0.57
    wit
    -0.55
     Dealer
    -0.55
    itect
    -0.55
    skinned
    -0.54
    POSITIVE LOGITS
    inel
    1.52
    entious
    1.09
    enced
    1.08
    imental
    1.07
     packing
    1.03
    ience
    0.87
     forth
    0.85
     abroad
    0.83
     home
    0.83
    ries
    0.80
    Activations Density 0.032%

    No Known Activations