© 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. 10-RES-JB
    11. 19035
    Prev
    Next
    INDEX
    Explanations

    phrases related to accomplishment, approval, and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or emotional reactions

    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
     charter
    -0.89
     credential
    -0.83
     multim
    -0.82
     automobile
    -0.81
     statewide
    -0.80
     divest
    -0.79
     stringent
    -0.78
     multinational
    -0.76
     Carnegie
    -0.75
     sophisticated
    -0.75
    POSITIVE LOGITS
    Reply
    1.36
    Anyway
    1.25
    EDIT
    1.22
    Trivia
    1.22
    lol
    1.21
    Alright
    1.20
     Reply
    1.15
    Yeah
    1.10
    âĶĢâĶĢâĶĢâĶĢ
    1.10
    Favorite
    1.09
    Activations Density 0.544%

    No Known Activations