© 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 EvalsExportsAPI 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. 20717
    Prev
    Next
    INDEX
    Explanations

    phrases related to failure or neglect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating failure or shortcomings in various contexts

    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
    moil
    -0.88
    loss
    -0.72
    interrupted
    -0.68
    anian
    -0.67
     Panic
    -0.65
     downfall
    -0.64
    adel
    -0.62
    urry
    -0.62
    gdala
    -0.60
     Mayhem
    -0.59
    POSITIVE LOGITS
     adequately
    1.17
     properly
    0.99
     adequate
    0.97
     enough
    0.81
     timely
    0.80
     stewards
    0.80
     proper
    0.80
     truthful
    0.80
     Proper
    0.79
     nutritious
    0.78
    Activations Density 1.005%

    No Known Activations