© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20476
    Prev
    Next
    INDEX
    Explanations

    Negative emotions, particularly feelings of anger and confusion

    oai_token-act-pair · gpt-3.5-turbo

    instances of confusion or emotional reactions

    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
    ESE
    -0.92
    itures
    -0.83
    çīĪ
    -0.81
     Selection
    -0.81
    ufact
    -0.79
    DragonMagazine
    -0.78
    imum
    -0.78
    etheus
    -0.75
    ONSORED
    -0.74
     Sequence
    -0.72
    POSITIVE LOGITS
     tired
    0.92
     gigg
    0.90
     uncontroll
    0.90
     sore
    0.89
     helpless
    0.87
     disillusion
    0.86
     sweaty
    0.85
     bruised
    0.85
     lonely
    0.84
     confused
    0.82
    Activations Density 0.277%

    No Known Activations