© 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. 18758
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts to contact for comments or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contact or communication attempts

    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
     subp
    -0.59
    Fit
    -0.55
    comes
    -0.54
    ever
    -0.53
     aspir
    -0.52
    ãĥĻ
    -0.52
     instituted
    -0.51
     decorations
    -0.51
     preached
    -0.51
     clipboard
    -0.50
    POSITIVE LOGITS
     by
    0.78
     via
    0.74
    =-=-=-=-
    0.74
    ONSORED
    0.70
    ragon
    0.65
    OHN
    0.65
    dinand
    0.64
    via
    0.64
    By
    0.63
    heastern
    0.63
    Activations Density 0.071%

    No Known Activations