© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6349
    Prev
    Next
    INDEX
    Explanations

    words related to efficiency or efforts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of efficiency or effective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.78
    Root
    -0.76
    Plex
    -0.73
    SpaceEngineers
    -0.72
    kaya
    -0.67
    ################################
    -0.66
    Wars
    -0.66
     Solitaire
    -0.66
    Story
    -0.65
    AU
    -0.65
    POSITIVE LOGITS
     eff
    1.08
    endi
    1.03
    luent
    0.91
    iency
    0.90
    rites
    0.90
    emin
    0.89
    ¥ŀ
    0.87
    encing
    0.86
    itt
    0.85
    monton
    0.83
    Activations Density 0.006%

    No Known Activations