© 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. 7-RES-JB
    11. 20910
    Prev
    Next
    INDEX
    Explanations

    references to sports events and competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to the Olympics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hirt
    -0.75
    tre
    -0.73
    BILITIES
    -0.69
     lodged
    -0.68
     wield
    -0.66
    phabet
    -0.66
     %%
    -0.64
    Choice
    -0.63
    soever
    -0.63
    chell
    -0.63
    POSITIVE LOGITS
     conjunction
    1.22
     lieu
    1.19
     spite
    1.03
     accordance
    1.01
     vitro
    1.01
     regards
    0.95
     favor
    0.92
     honor
    0.92
     hopes
    0.90
     vain
    0.89
    Activations Density 0.318%

    No Known Activations