© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opposition or caution

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opposition and calls to action against various issues

    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
     calmed
    -0.78
    ortality
    -0.76
    ector
    -0.75
    albeit
    -0.74
    eline
    -0.73
    oglobin
    -0.70
    hesion
    -0.70
    si
    -0.70
    irement
    -0.70
    mma
    -0.69
    POSITIVE LOGITS
     unnecessary
    1.16
     undue
    1.14
     wasteful
    1.13
     excessive
    1.13
     wasting
    1.07
     needless
    1.07
     duplication
    1.03
     discriminatory
    1.02
     improper
    1.02
     discrimination
    1.01
    Activations Density 0.272%

    No Known Activations