© 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. 9325
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts or disputes

    oai_token-act-pair · gpt-3.5-turbo

    situations involving critical decisions or actions taken under pressure

    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
    hovah
    -0.82
     MFT
    -0.69
     HERE
    -0.61
    +)
    -0.58
    miah
    -0.56
     overlap
    -0.56
    ebin
    -0.56
     (~
    -0.56
     consists
    -0.56
    razil
    -0.56
    POSITIVE LOGITS
     himself
    0.72
    arted
    0.62
    çİĭ
    0.61
     nerves
    0.59
    Ire
    0.58
     unworthy
    0.57
     inexper
    0.57
     manoeuv
    0.57
    æĿ
    0.56
    ãĥĦ
    0.56
    Activations Density 1.673%

    No Known Activations