© 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. 10-RES-JB
    11. 4344
    Prev
    Next
    INDEX
    Explanations

    phrases related to critique and evaluation, especially in the context of reviews or analysis

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding opinions or perceptions about individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     programmes
    -0.59
     Occupations
    -0.59
     guiIcon
    -0.57
    adays
    -0.57
    doors
    -0.56
     Controls
    -0.56
    sbm
    -0.56
    SpaceEngineers
    -0.55
     controls
    -0.55
     Everywhere
    -0.54
    POSITIVE LOGITS
     warranted
    0.84
     chuckle
    0.81
     conclusions
    0.80
     conjecture
    0.79
     disingen
    0.78
     nit
    0.77
    argument
    0.77
     glean
    0.76
     conclusion
    0.76
     reader
    0.75
    Activations Density 0.734%

    No Known Activations