© 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. 9375
    Prev
    Next
    INDEX
    Explanations

    legal terms related to representing someone or a group of people

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "on behalf of"

    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
    ById
    -0.67
     Rasmussen
    -0.65
    frey
    -0.62
    Spoiler
    -0.61
     typo
    -0.61
    Ku
    -0.60
    ANG
    -0.60
    Nin
    -0.60
    enty
    -0.60
     Eps
    -0.59
    POSITIVE LOGITS
    giving
    0.78
    eering
    0.76
    heet
    0.75
    awaru
    0.75
     behalf
    0.74
    atography
    0.73
    clinton
    0.72
    avement
    0.67
    ours
    0.66
    ship
    0.66
    Activations Density 0.011%

    No Known Activations