© 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. 6-RES-JB
    11. 9406
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that start with "Everyone" or "everybody"

    oai_token-act-pair · gpt-3.5-turbo

    references to "everyone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anga
    -0.65
    pose
    -0.62
    QL
    -0.62
    eln
    -0.60
    Son
    -0.58
    sole
    -0.58
     Kamp
    -0.58
     guiActiveUnfocused
    -0.58
    vern
    -0.57
    duc
    -0.57
    POSITIVE LOGITS
     else
    1.59
     Else
    1.07
     imaginable
    1.05
    THING
    1.05
    else
    0.98
     conceivable
    0.90
    Else
    0.88
     who
    0.79
    body
    0.78
    ocating
    0.76
    Activations Density 0.037%

    No Known Activations