© 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. 0-RES-JB
    11. 2223
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaining something, such as gaining asylum, gaining weight, or gaining ground

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "gained" and its variations, typically in contexts of acquiring something

    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
    zing
    -0.59
     tomorrow
    -0.59
    ror
    -0.57
     directions
    -0.56
     mosquit
    -0.55
    Um
    -0.55
     dere
    -0.55
     Semi
    -0.55
    amin
    -0.55
     Schedule
    -0.54
    POSITIVE LOGITS
     gained
    3.50
     regained
    2.09
     gain
    1.88
     garnered
    1.83
     gaining
    1.78
     gains
    1.75
     attained
    1.71
     achieved
    1.60
    gain
    1.58
     obtained
    1.57
    Activations Density 0.009%

    No Known Activations