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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 18370
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement or advancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Better" and its variations related to improvements or enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trl
    -0.81
    FK
    -0.77
    wart
    -0.74
    eur
    -0.73
    dom
    -0.72
    warts
    -0.71
    MIT
    -0.69
    icidal
    -0.68
    í
    -0.68
    orial
    -0.68
    POSITIVE LOGITS
     Better
    1.04
     Than
    0.99
     Faster
    0.92
    Better
    0.78
     Neigh
    0.73
     Tune
    0.73
     Quality
    0.72
    than
    0.71
     Friends
    0.71
     Answers
    0.70
    Activations Density 0.011%

    No Known Activations