© 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. 0-RES-JB
    11. 12710
    Prev
    Next
    INDEX
    Explanations

    names and references related to a specific media company

    oai_token-act-pair · gpt-3.5-turbo

    references to the Marvel Cinematic Universe (MCU)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recep
    -0.78
    Turkey
    -0.77
     tsunami
    -0.70
    osate
    -0.70
    Wisconsin
    -0.69
     deflation
    -0.69
    Turkish
    -0.68
     Turkey
    -0.68
     Turk
    -0.68
     Erdogan
    -0.66
    POSITIVE LOGITS
     MC
    4.03
    MC
    2.22
     mc
    1.95
    mc
    1.80
     MV
    1.30
     DM
    1.29
     MU
    1.27
     DJ
    1.25
     MF
    1.19
     MM
    1.16
    Activations Density 0.012%

    No Known Activations