© 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. 6-RES-JB
    11. 12056
    Prev
    Next
    INDEX
    Explanations

    phrases expressing disagreement or disillusionment

    oai_token-act-pair · gpt-3.5-turbo

    statements that highlight negation or contradiction regarding expectations or beliefs

    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
     redes
    -0.78
    çīĪ
    -0.69
     ACTIONS
    -0.66
    asionally
    -0.63
     periodically
    -0.62
    YES
    -0.61
    姫
    -0.61
     margins
    -0.61
     unsus
    -0.60
    )))
    -0.59
    POSITIVE LOGITS
     anymore
    1.72
     nor
    1.34
    yet
    1.09
     necessarily
    0.98
     slightest
    0.90
     anybody
    0.85
     anywhere
    0.83
     yet
    0.81
    necess
    0.78
     any
    0.78
    Activations Density 0.316%

    No Known Activations