© 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. 6-RES-JB
    11. 5035
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments or expressions of uncertainty

    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
    pse
    -0.66
    rex
    -0.66
    often
    -0.65
    late
    -0.65
    lass
    -0.64
    adobe
    -0.64
    interstitial
    -0.64
    tenance
    -0.64
    DragonMagazine
    -0.63
     srf
    -0.63
    POSITIVE LOGITS
     clue
    1.03
     doubt
    1.01
     earthly
    0.93
     qual
    0.90
     illusions
    0.90
     chance
    0.90
     recourse
    0.89
     intention
    0.89
     discern
    0.87
     shortage
    0.87
    Activations Density 0.039%

    No Known Activations