© 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. 11-RES-JB
    11. 11405
    Prev
    Next
    INDEX
    Explanations

    words related to official positions or statements

    oai_token-act-pair · gpt-3.5-turbo

    the term "official" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rums
    -0.75
    ĸļ
    -0.74
    bane
    -0.70
    OPE
    -0.69
    abeth
    -0.68
    different
    -0.67
    century
    -0.66
    vant
    -0.66
    ocene
    -0.66
    esville
    -0.66
    POSITIVE LOGITS
    dom
    1.21
     Opposition
    0.86
     scorer
    0.84
     announcement
    0.84
    ities
    0.80
     confirmation
    0.80
     designation
    0.78
     explanation
    0.77
     documentation
    0.76
     transcript
    0.76
    Activations Density 0.061%

    No Known Activations