© 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. 12041
    Prev
    Next
    INDEX
    Explanations

    sources or informants providing information

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
    Interstitial
    -0.75
     ILCS
    -0.73
     mascot
    -0.67
    ample
    -0.65
    served
    -0.64
    earable
    -0.64
    Compan
    -0.64
    ãĤª
    -0.61
    Herm
    -0.60
    POSITIVE LOGITS
     BuzzFeed
    1.21
     POLITICO
    1.15
     Reuters
    1.15
     Politico
    1.10
     Newsweek
    1.04
     HuffPost
    0.98
     CNN
    0.98
     ESPN
    0.96
     Fairfax
    0.96
     Quartz
    0.96
    Activations Density 0.057%

    No Known Activations