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

    Neuronpedia

    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. 8542
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or division within a group

    oai_token-act-pair · gpt-3.5-turbo
    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
     Saying
    -0.71
     Loading
    -0.70
    OOL
    -0.70
     Recap
    -0.68
     disclaimer
    -0.67
    package
    -0.65
    arter
    -0.64
     Quote
    -0.63
     Correction
    -0.60
     opener
    -0.60
    POSITIVE LOGITS
     been
    1.34
     arisen
    1.18
     hitherto
    1.11
     risen
    1.07
    been
    1.06
     become
    1.02
     existed
    1.01
     resided
    0.99
     fallen
    0.99
     gotten
    0.97
    Activations Density 0.151%

    No Known Activations