© 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. 9-RES-JB
    11. 11202
    Prev
    Next
    INDEX
    Explanations

    phrases related to caution or warning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that caution against negative actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.70
    ilogy
    -0.68
    ourses
    -0.67
    leground
    -0.66
     stabilized
    -0.64
    albeit
    -0.63
     unparalleled
    -0.60
    ially
    -0.59
     correspond
    -0.58
     ancest
    -0.56
    POSITIVE LOGITS
     yourselves
    1.24
     yourself
    1.17
     Yourself
    1.02
     fooled
    0.91
     anymore
    0.83
     blindly
    0.81
     your
    0.78
    ãĤ®
    0.77
     ANY
    0.76
     fool
    0.76
    Activations Density 0.251%

    No Known Activations